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. 16258
    Prev
    Next
    INDEX
    Explanations

    information about broadcasting stations

    oai_token-act-pair · gemini-2.0-flash

    Arkansas

    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
    ="@+
    -0.71
     生命周期
    -0.63
    InputBorder
    -0.62
     Audiodateien
    -0.60
    TestingModule
    -0.59
     pleaſure
    -0.59
     snippetHide
    -0.58
    ReusableCell
    -0.56
     insuffisamment
    -0.56
    ])[
    -0.56
    POSITIVE LOGITS
    LabelTagHelper
    0.52
    ยะ
    0.49
    RowCount
    0.49
    hoi
    0.42
    ongo
    0.42
    queryInterface
    0.41
    สอบ
    0.40
     zboží
    0.40
    níci
    0.40
     tasted
    0.39
    Activations Density 0.726%

    No Known Activations