© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3109
    Prev
    Next
    INDEX
    Explanations

    computer code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     AssemblyCulture
    -0.70
     StatelessWidget
    -0.62
    )">
    -0.61
    /***/
    -0.57
    <bos>
    -0.56
     trimester
    -0.56
    '");
    -0.56
    }{*}{}
    -0.56
    </thead>
    -0.55
    numerusform
    -0.55
    POSITIVE LOGITS
    PMailer
    0.78
    ̣n
    0.60
    ksikon
    0.56
     Phal
    0.54
    Tembelea
    0.53
    atív
    0.52
    र्शन
    0.52
    لمانيا
    0.52
    Parcelize
    0.52
     niềm
    0.51
    Activations Density 2.483%

    No Known Activations