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. 16364
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating location or affiliation

    oai_token-act-pair · gemini-2.0-flash

    locations

    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
     صوتيه
    -0.77
    ValueStyle
    -0.75
     Jefus
    -0.70
     ſche
    -0.68
     itſelf
    -0.66
    MLLoader
    -0.65
     ویکی‌پدیای
    -0.65
    Maße
    -0.65
     iſt
    -0.64
     }</
    -0.62
    POSITIVE LOGITS
    Portale
    0.49
     den
    0.49
     light
    0.41
     boca
    0.39
    Controls
    0.38
     bez
    0.38
     lan
    0.37
    ILING
    0.37
     dos
    0.36
     Cumming
    0.36
    Activations Density 1.288%

    No Known Activations