© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12212
    Prev
    Next
    INDEX
    Explanations

    text describing the plot and characters of the Transformers franchise

    oai_token-act-pair · gemini-2.0-flash

    of

    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
     public
    -0.65
    SourceChecksum
    -0.62
    Public
    -0.62
    MessageOf
    -0.61
     Public
    -0.57
     público
    -0.56
    ArrowToggle
    -0.54
     PUBLIC
    -0.53
    msgTypes
    -0.52
    wußt
    -0.52
    POSITIVE LOGITS
    帖最后由
    0.57
    ()]);
    0.55
    })).
    0.55
    })),
    0.52
     conseille
    0.51
    kule
    0.51
    ])){
    0.50
    )))
    0.50
    ugc
    0.49
    }))
    0.48
    Activations Density 2.122%

    No Known Activations