© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211912
    Prev
    Next
    INDEX
    Explanations

    "on-device" AI

    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_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    জ্জ
    0.43
    த்தா
    0.41
    身份
    0.40
     ujarnya
    0.39
     STRA
    0.39
    舢
    0.39
    unción
    0.39
     운동
    0.38
    शिंगटन
    0.38
    htra
    0.38
    POSITIVE LOGITS
    R
    0.41
     ไม่
    0.40
     R
    0.39
    ceral
    0.38
     cheat
    0.38
     שלא
    0.37
     calculate
    0.37
     resolve
    0.37
     avoid
    0.36
    up
    0.36
    Activations Density 0.028%

    No Known Activations