© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93996
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    Offer
    0.56
     offer
    0.54
     Offer
    0.53
    offer
    0.47
    你
    0.46
    You
    0.46
     реакции
    0.46
    !:
    0.43
    反应
    0.43
    คุณ
    0.42
    POSITIVE LOGITS
     great
    1.66
    great
    1.45
     вели
    1.29
     GREAT
    1.05
    GREAT
    0.98
    Great
    0.82
     Great
    0.77
     grande
    0.67
     महान
    0.57
     grandes
    0.55
    Activations Density 0.008%

    No Known Activations