© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11618
    Prev
    Next
    INDEX
    Explanations

    text features like hyphens, currency symbols, and HTML.

    oai_token-act-pair · gemini-2.0-flash

    dashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    is
    -0.65
    makeConstraints
    -0.58
    more
    -0.58
    IS
    -0.56
    one
    -0.55
    mere
    -0.54
    all
    -0.53
     
    -0.52
    și
    -0.50
    '])){
    -0.49
    POSITIVE LOGITS
    StoryboardSegue
    0.59
    encils
    0.59
     jspb
    0.59
    that
    0.57
     متعلقه
    0.55
    ofing
    0.54
     Cataloging
    0.54
    ضير
    0.54
    ucson
    0.53
     ProtoMessage
    0.53
    Activations Density 13.165%

    No Known Activations