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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14173
    Prev
    Next
    INDEX
    Explanations

    technical words describing something that is high quality

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
    Билгалдахарш
    -0.97
    twimg
    -0.88
     MainAxisSize
    -0.84
     ModelExpression
    -0.82
    sizeCache
    -0.81
    ContentAsync
    -0.81
    AndEndTag
    -0.80
    webElementXpaths
    -0.80
    IntoConstraints
    -0.77
     يتيمه
    -0.77
    POSITIVE LOGITS
     kres
    0.49
    imanapun
    0.47
    PageContext
    0.45
    ifun
    0.45
    AUTH
    0.43
     Priya
    0.43
     Lacy
    0.42
     SIGNAL
    0.42
    fant
    0.42
    Silent
    0.41
    Activations Density 1.336%

    No Known Activations