© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10658
    Prev
    Next
    INDEX
    Explanations

    dashes adjacent to other punctuation, numbers, or symbols

    oai_token-act-pair · gemini-2.0-flash

    dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     esternos
    -0.82
    
    -0.77
    Välislingid
    -0.71
    keyColumn
    -0.61
     ویکی‌پدی
    -0.60
    MIDDLEWARE
    -0.60
     الاطلاع
    -0.60
    Hentet
    -0.56
     cherchés
    -0.54
     isComment
    -0.54
    POSITIVE LOGITS
    ScopeManager
    0.44
     BoxFit
    0.42
    ους
    0.40
    tagHelperRunner
    0.40
    DispatchToProps
    0.40
     dischar
    0.38
     herewith
    0.38
     offici
    0.38
    Izvori
    0.38
    urp
    0.37
    Activations Density 1.693%

    No Known Activations