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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1594
    Prev
    Next
    INDEX
    Explanations

    abbreviations of USA locations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    ,
    -1.34
    .
    -1.13
    ;
    -0.99
    :
    -0.98
    )
    -0.97
    ”
    -0.93
    ,”
    -0.92
    .”
    -0.91
    ,"
    -0.91
    .}
    -0.90
    POSITIVE LOGITS
     quæ
    0.68
     habet
    0.59
     ejus
    0.55
     eorum
    0.51
     ainfi
    0.45
     avoient
    0.44
     feroit
    0.42
     auffi
    0.40
    amerikanischer
    0.40
     auroit
    0.40
    Activations Density 8.129%

    No Known Activations