© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12171
    Prev
    Next
    INDEX
    Explanations

    parentheses, brackets, and percentage signs occurring in mathematical or legal writing

    oai_token-act-pair · gemini-2.0-flash

    parenthesis/brackets

    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
     }</
    -0.65
    o
    -0.63
    s
    -0.59
    i
    -0.58
     {,
    -0.58
    )}</
    -0.57
     BrowserModule
    -0.56
     </
    -0.55
    ije
    -0.54
     Réponses
    -0.54
    POSITIVE LOGITS
    (
    1.52
    "
    1.21
    $
    1.14
    -
    1.10
    \
    1.05
    0.90
    )
    0.82
    [
    0.82
    /
    0.78
    :
    0.77
    Activations Density 4.029%
    No Known Activations