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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5838
    Prev
    Next
    INDEX
    Explanations

    rhyming poetry

    oai_token-act-pair · gemini-2.0-flash

    technical terms or code-related words

    np_token-act-pair-logits · gpt-4o-mini

    code and foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    ьогодні
    -0.46
     effetti
    -0.45
     combinaison
    -0.44
    prepareStatement
    -0.43
     the
    -0.39
     himo
    -0.38
     programmet
    -0.38
     anuncios
    -0.38
     resourceCulture
    -0.38
    Approximate
    -0.38
    POSITIVE LOGITS
    KEYCODE
    0.91
     ويكيميديا
    0.85
     FetchType
    0.84
     виправивши
    0.84
    posedge
    0.78
    TestingModule
    0.78
     Wicidata
    0.75
     ―――――
    0.75
    JNIEnv
    0.75
     ویکی‌پدیای
    0.75
    Activations Density 0.344%

    No Known Activations