Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14248
    Prev
    Next
    INDEX
    Explanations

    the letters "t" and "o" at the end of words

    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
     الحره
    -1.03
     Infórmanos
    -0.95
    tagHelperRunner
    -0.93
    findpost
    -0.93
    oredCriteria
    -0.91
     समीक्षक
    -0.88
     createSlice
    -0.82
    ConstraintMaker
    -0.79
    KommentareTeilen
    -0.79
     مواليد
    -0.79
    POSITIVE LOGITS
     consecration
    0.41
    hey
    0.39
    ברי
    0.39
    末
    0.39
     paging
    0.38
     Lest
    0.38
     WaitFor
    0.37
     semantic
    0.37
     apology
    0.37
     lais
    0.37
    Activations Density 0.813%

    No Known Activations