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. 16307
    Prev
    Next
    INDEX
    Explanations

    a mix of chemical formulas, links to websites, and mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    chemical formulas and equations

    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
    setVerticalGroup
    -0.76
    enumii
    -0.73
     متعلقه
    -0.73
    DockStyle
    -0.63
     ***!
    -0.63
    <bos>
    -0.61
    uxxxx
    -0.60
    JspWriter
    -0.57
     Vikipedi
    -0.57
     AssemblyCulture
    -0.57
    POSITIVE LOGITS
     linkovi
    0.48
    contentLoaded
    0.47
    swig
    0.47
     می‌گوید
    0.47
    يكية
    0.45
     trône
    0.45
     opini
    0.44
    #%%
    0.44
    assertAll
    0.44
     vocal
    0.43
    Activations Density 1.995%

    No Known Activations