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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16159
    Prev
    Next
    INDEX
    Explanations

    URLs, especially those related to software development and crowdfunding

    oai_token-act-pair · gemini-2.0-flash

    URLs in code or documentation

    np_token-act-pair-logits · gemini-2.0-flash

    github

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     disambiguazione
    -0.51
    ]--;
    -0.42
    __);
    -0.42
    ɵ
    -0.41
    setObject
    -0.41
    娶
    -0.41
    lably
    -0.40
    settling
    -0.40
     amare
    -0.40
    Its
    -0.40
    POSITIVE LOGITS
    帖最后由
    0.66
    NameInMap
    0.63
     مواليد
    0.58
    UnusedPrivate
    0.57
    مصادر
    0.57
     ostavi
    0.56
    Clik
    0.54
    ьаж
    0.54
     tartalomajánló
    0.54
    ANDUM
    0.53
    Activations Density 1.395%

    No Known Activations