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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16352
    Prev
    Next
    INDEX
    Explanations

    technical academic or scientific language

    oai_token-act-pair · gemini-2.0-flash

    otides

    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
     HasFactory
    -0.74
     contextLoads
    -0.71
     pleaſure
    -0.71
     myſelf
    -0.70
     faſt
    -0.69
     vixion
    -0.67
    WebVitals
    -0.67
     fubject
    -0.66
     ſmall
    -0.66
     ſeveral
    -0.66
    POSITIVE LOGITS
     en
    0.66
    UnknownFieldSet
    0.55
     con
    0.54
     encode
    0.52
    RestController
    0.50
     tương
    0.50
    ice
    0.48
    rrggbb
    0.48
     imp
    0.47
     kasarigan
    0.47
    Activations Density 4.294%

    No Known Activations