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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9149
    Prev
    Next
    INDEX
    Explanations

    Here

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    th
    0.70
     უ
    0.67
     புக
    0.66
     Kombination
    0.65
     latter
    0.65
     নাম
    0.65
    મા
    0.64
    Ở
    0.63
    wä
    0.62
    ்ட்ட
    0.60
    POSITIVE LOGITS
     ඔබේ
    0.67
     याचा
    0.67
     habló
    0.66
    чит
    0.66
    🍁
    0.66
    ologo
    0.65
    తున్న
    0.65
    ㊙
    0.64
     ваша
    0.63
    prefs
    0.63
    Activations Density 0.152%

    No Known Activations