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. 16310
    Prev
    Next
    INDEX
    Explanations

    seemingly random punctuation and spacing in code or formal documents.

    oai_token-act-pair · 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
    ///</
    -0.70
     незавершена
    -0.67
     <=",
    -0.64
    AxisAlignment
    -0.64
    glBegin
    -0.60
     متعلقه
    -0.59
     الدولى
    -0.59
    BeginInit
    -0.59
    లాలు
    -0.58
    InjectMocks
    -0.57
    POSITIVE LOGITS
    нок
    0.47
    verifyException
    0.47
    kegaard
    0.47
     Relief
    0.46
     respite
    0.46
    Glej
    0.45
    uarga
    0.45
    uchten
    0.45
    getColumnIndex
    0.45
    rillos
    0.45
    Activations Density 4.261%

    No Known Activations