© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44164
    Prev
    Next
    INDEX
    Explanations

    дня

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    p
    0.70
     ﺍ
    0.67
     APPENDIX
    0.66
    f
    0.65
    t
    0.62
    ó
    0.61
     ideje
    0.61
    ेशर
    0.60
     abrió
    0.60
     beş
    0.60
    POSITIVE LOGITS
    0
    0.78
    る
    0.66
    تها
    0.66
    ्स
    0.65
    ‌ها
    0.64
    นำ
    0.63
    น้ำ
    0.61
     distancing
    0.60
    ને
    0.57
    นะ
    0.57
    Activations Density 0.005%

    No Known Activations