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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14183
    Prev
    Next
    INDEX
    Explanations

    terms related to circuits and digital logic

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
    例句
    -0.45
    enumii
    -0.45
    CMS
    -0.42
    iertas
    -0.41
     mou
    -0.40
     Runde
    -0.40
    DockStyle
    -0.39
     redan
    -0.39
    tikzpicture
    -0.37
    ◎
    -0.37
    POSITIVE LOGITS
     disambiguazione
    0.91
    PreferredItem
    0.87
    thâu
    0.81
    AndEndTag
    0.79
    LLocation
    0.77
    ValueStyle
    0.75
    Personensuche
    0.75
    OGND
    0.70
     nahilalakip
    0.69
    دانشنامهٔ
    0.69
    Activations Density 2.065%

    No Known Activations