© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13459
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations, politics, and workplaces with an emphasis on measurable data

    oai_token-act-pair · gemini-2.0-flash

    Institutions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     becauſe
    -0.84
     Shakspeare
    -0.82
     myſelf
    -0.80
    exitRule
    -0.75
     itſelf
    -0.72
     Jefus
    -0.70
     Monfieur
    -0.69
    oa̍t
    -0.68
     betweenstory
    -0.67
    NUMX
    -0.67
    POSITIVE LOGITS
     sık
    0.47
    Drawing
    0.45
     만
    0.42
    zunehmen
    0.40
     da
    0.40
    kesan
    0.40
    DispatchToProps
    0.40
    acon
    0.39
    gör
    0.39
    Uns
    0.38
    Activations Density 1.494%

    No Known Activations