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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1573
    Prev
    Next
    INDEX
    Explanations

    text describing digital circuit designs

    oai_token-act-pair · gemini-2.0-flash

    clock

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    OGND
    -0.82
    styleable
    -0.66
    MLLoader
    -0.65
    URLException
    -0.60
    TypedDataSet
    -0.60
    Geplaatst
    -0.60
    InputBorder
    -0.60
    <?
    -0.59
     ModelExpression
    -0.59
     Lordships
    -0.59
    POSITIVE LOGITS
    ǔ
    0.55
    paigns
    0.47
    addPreferredGap
    0.46
     dq
    0.46
     interpolation
    0.46
    Pts
    0.46
    pts
    0.45
     altrett
    0.45
     tune
    0.44
     freq
    0.43
    Activations Density 12.231%

    No Known Activations