© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10136
    Prev
    Next
    INDEX
    Explanations

    intimate interactions Method used: 2, Reason: Texts share a theme of personal, intimate, or sexually charged narratives, Evidence: Sexually explicit language and personal stories

    np_max-act · claude-3-5-haiku-20241022Triggered by @strawberryfrappe

    language related to physical activity, pushing, and exertion, or language used by coaches and athletes.

    oai_token-act-pair · gemini-2.0-flash

    Explicit content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    •A

    No Comments

    Negative Logits
     fufficient
    -0.94
     sufficient
    -0.87
     fuper
    -0.81
     fevere
    -0.81
     Obtain
    -0.80
     neceffary
    -0.79
     Sufficient
    -0.79
     Insufficient
    -0.79
    sufficient
    -0.79
    obtained
    -0.79
    POSITIVE LOGITS
    +#+
    0.63
    TagMode
    0.56
    SourceChecksum
    0.51
    __))
    0.48
    }$}
    0.47
     kasarigan
    0.46
    viewDidLoad
    0.44
    ]]
    0.43
    }">
    0.43
    oplayer
    0.41
    Activations Density 17.495%

    No Known Activations