© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7432
    Prev
    Next
    INDEX
    Explanations

    lines that start with whitespace

    oai_token-act-pair · gemini-2.0-flash

    tokens with underscore prefix

    np_token-act-pair-logits · gpt-4o-mini

    technical document

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    .
    -0.40
    <eos>
    -0.37
     we
    -0.36
     o
    -0.36
     нау
    -0.35
    ,
    -0.35
    rxjs
    -0.34
    *
    -0.34
    yargs
    -0.34
    眼鏡
    -0.33
    POSITIVE LOGITS
    expandindo
    1.09
    windowFixed
    1.09
     autorytatywna
    1.03
    MigrationBuilder
    0.98
     OFDb
    0.92
    évaluateur
    0.92
     betweenstory
    0.91
    ValueStyle
    0.90
    RenderAtEndOf
    0.88
    AutoresizingMask
    0.86
    Activations Density 0.454%

    No Known Activations