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. 1703
    Prev
    Next
    INDEX
    Explanations

    technical documents and website code

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    UnusedPrivate
    -0.75
    EndProject
    -0.73
     ExecuteAsync
    -0.60
    Autoritní
    -0.59
    makeConstraints
    -0.59
    UpInside
    -0.58
    A
    -0.58
     disambiguazione
    -0.57
    Personensuche
    -0.57
     AssemblyTitle
    -0.57
    POSITIVE LOGITS
     برانيه
    0.50
    WithTag
    0.48
     pêche
    0.48
    Portale
    0.47
     IActionResult
    0.46
    Citiți
    0.45
     estimés
    0.44
    InputElement
    0.43
    ————————————————
    0.43
     poudre
    0.43
    Activations Density 4.490%

    No Known Activations