© 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. 23953
    Prev
    Next
    INDEX
    Explanations

    code closing parentheses

    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
    in
    1.16
    ↵
    0.91
    د
    0.86
     set
    0.82
    inä
    0.79
    鍑
    0.78
    ्य
    0.77
     (
    0.76
    ribut
    0.75
    y
    0.73
    POSITIVE LOGITS
     ناحيه
    0.98
    هي
    0.92
     énfasis
    0.91
    يد
    0.88
    اري
    0.85
    وري
    0.84
    ৯
    0.84
     canaux
    0.84
     ايجاد
    0.84
     nosso
    0.83
    Activations Density 0.025%

    No Known Activations