© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48408
    Prev
    Next
    INDEX
    Explanations

    say "ed" words

    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_55_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
    디
    1.61
    ディ
    1.57
    די
    1.53
    迪
    1.46
    Adi
    1.45
    ди
    1.43
     Adi
    1.41
    ДИ
    1.41
    ADI
    1.40
     ди
    1.37
    POSITIVE LOGITS
    ダ
    0.57
     ダ
    0.56
     dand
    0.52
     Darn
    0.49
     dart
    0.48
     Dand
    0.47
    ドー
    0.47
     darn
    0.46
     Dar
    0.45
     داله
    0.45
    Activations Density 0.017%

    No Known Activations