Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16318
    Prev
    Next
    INDEX
    Explanations

    java code imports and class definition info

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ($__
    -0.67
    abestanden
    -0.63
    awtextra
    -0.60
    oredCriteria
    -0.60
     bezig
    -0.57
    XmlAccessType
    -0.54
    Portály
    -0.54
    StoredProcedure
    -0.53
     intptr
    -0.52
    таратура
    -0.52
    POSITIVE LOGITS
    URLException
    0.64
    databind
    0.53
    Décès
    0.52
    onViewCreated
    0.49
     ويكيميديا
    0.48
    ViewInit
    0.48
    뀐
    0.47
     AssemblyTitle
    0.47
    ÚBL
    0.47
    новниш
    0.45
    Activations Density 0.306%

    No Known Activations