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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16235
    Prev
    Next
    INDEX
    Explanations

    references to fractional numbers or units of time/distance.

    oai_token-act-pair · gemini-2.0-flash

    fractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
     unknownFields
    -0.77
    hObject
    -0.59
     pinulongan
    -0.59
    Autoritní
    -0.56
    ]-'
    -0.55
    بوابة
    -0.55
     SwitchCompat
    -0.54
    Personendaten
    -0.52
    DataAnnotations
    -0.51
    Наводи
    -0.50
    POSITIVE LOGITS
    expandindo
    0.65
    脚注の使い方
    0.62
    <?
    0.54
    ilver
    0.53
     defStyle
    0.52
    idian
    0.50
     spett
    0.49
     Turning
    0.48
     million
    0.48
    archiviato
    0.48
    Activations Density 0.562%

    No Known Activations