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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14273
    Prev
    Next
    INDEX
    Explanations

    measurements and units

    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
     resourceCulture
    -0.54
    createClass
    -0.54
    office
    -0.49
    ↘
    -0.46
    UV
    -0.46
    abestanden
    -0.45
    Carriera
    -0.45
    EndProject
    -0.44
     &___
    -0.44
     office
    -0.44
    POSITIVE LOGITS
     Inches
    0.77
     inches
    0.76
    Inches
    0.69
    inches
    0.68
     inch
    0.66
     Fahrenheit
    0.65
    inch
    0.64
     MessageBoxIcon
    0.62
     wireType
    0.62
     Celsius
    0.60
    Activations Density 0.580%

    No Known Activations