© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3655
    Prev
    Next
    INDEX
    Explanations

    code snippets, mathematical equations, or elements of structured documents marked up with HTML or similar

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    dolu
    -0.59
    agisse
    -0.58
     Theil
    -0.57
    úgó
    -0.57
    Rüyada
    -0.57
    queous
    -0.56
    geries
    -0.54
    IntoConstraints
    -0.54
    )";
    -0.54
    )");
    -0.52
    POSITIVE LOGITS
    \"
    0.67
    [
    0.66
    MessageOf
    0.65
    ^
    0.63
    <
    0.61
    ../
    0.60
    {
    0.59
    \,
    0.58
     AppBundle
    0.55
    HasForeignKey
    0.54
    Activations Density 11.539%

    No Known Activations