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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14111
    Prev
    Next
    INDEX
    Explanations

    code snippets with semicolons, parentheses, and other code syntax

    oai_token-act-pair · gemini-2.0-flash

    code symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     ivelany
    -0.67
     AssemblyVersion
    -0.59
    JsonPropertyName
    -0.54
    #+#
    -0.54
    setVerticalGroup
    -0.52
     menar
    -0.52
    ()?;
    -0.49
    UnusedPrivate
    -0.48
     otomatig
    -0.48
    verifyException
    -0.46
    POSITIVE LOGITS
    addCriterion
    0.57
    <eos>
    0.54
     pinulongan
    0.52
     مشين
    0.52
    SqlSession
    0.51
    Aiheesta
    0.50
     Playa
    0.49
    tawesome
    0.47
    Cyfeiriadau
    0.47
    rxjs
    0.47
    Activations Density 0.728%

    No Known Activations