© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2897
    Prev
    Next
    INDEX
    Explanations

    Nazi atrocities at Dachau

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    пад
    1.01
    нк
    0.95
     sinus
    0.91
     তবে
    0.88
     रिप्रोडक्शन
    0.88
    挝
    0.88
     नोएडा
    0.86
    াবের
    0.85
     расходы
    0.85
     somehow
    0.85
    POSITIVE LOGITS
    playlist
    0.89
    $-\
    0.88
    あった
    0.83
    supp
    0.81
    screening
    0.77
    ${
    0.77
    Vie
    0.74
    ోధ
    0.73
    स्टिव
    0.73
    FU
    0.73
    Activations Density 0.037%

    No Known Activations