© 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. 4029
    Prev
    Next
    INDEX
    Explanations

    legal claims or statements, often identified by surrounding punctuation

    oai_token-act-pair · 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
     [
    -2.95
    [
    -2.33
     $[
    -2.17
     [$
    -1.87
     [
    -1.84
     ["
    -1.79
     $[\
    -1.79
    }[
    -1.77
    [\
    -1.77
    -[
    -1.73
    POSITIVE LOGITS
    łasz
    0.55
    مصادر
    0.52
     initComponents
    0.49
    StandardCharsets
    0.48
    FetchType
    0.47
    ',(
    0.47
    )))));
    0.46
    //</
    0.44
     ?',
    0.44
     useDispatch
    0.44
    Activations Density 1.112%

    No Known Activations