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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16255
    Prev
    Next
    INDEX
    Explanations

    lines of code with a single number of indentations

    oai_token-act-pair · gemini-2.0-flash

    code snippets and logs

    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
    IsContent
    -0.61
    !*\
    -0.61
    OGND
    -0.61
    #+#
    -0.60
    :✨
    -0.57
    DoubleQuotes
    -0.56
    EDEFAULT
    -0.53
    TagHelpers
    -0.52
    ButterKnife
    -0.52
     تضيفلها
    -0.49
    POSITIVE LOGITS
    uskas
    0.53
     Ecclesiastical
    0.53
    StateList
    0.50
    foundland
    0.48
    liminary
    0.48
     GRADUATE
    0.47
    uguetes
    0.47
     NAL
    0.47
    læg
    0.46
     redwood
    0.45
    Activations Density 0.556%

    No Known Activations