© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220429
    Prev
    Next
    INDEX
    Explanations

    resolved a bug

    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_10_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
    arán
    0.49
     wind
    0.46
     بالش
    0.45
    ieren
    0.43
     바람
    0.43
    ää
    0.42
    em
    0.41
     <=
    0.41
    ará
    0.40
    inske
    0.40
    POSITIVE LOGITS
    ०
    0.50
    द
    0.50
     عظ
    0.49
     سمیت
    0.47
    ा
    0.46
    差し
    0.45
    큽
    0.45
     crum
    0.45
    तर
    0.44
     ocupa
    0.44
    Activations Density 0.000%

    No Known Activations