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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38639
    Prev
    Next
    INDEX
    Explanations

    paradigm shift

    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
    ков
    0.77
    тку
    0.73
    ƙ
    0.68
    ковь
    0.67
    洿
    0.64
    ેટ
    0.63
    지
    0.63
    ках
    0.62
    гуу
    0.62
    িত্যক্ত
    0.61
    POSITIVE LOGITS
     is
    1.02
    ↵
    0.81
    ।
    0.78
    Т
    0.75
     on
    0.72
    in
    0.71
     mít
    0.70
    lah
    0.70
    ré
    0.69
    on
    0.67
    Activations Density 0.001%

    No Known Activations