© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193306
    Prev
    Next
    INDEX
    Explanations

    suggestion or advice

    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_9_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
    ي
    1.30
    ി
    1.27
    ب
    1.27
    ル
    1.24
    م
    1.22
    H
    1.20
    ু
    1.18
    સ
    1.18
    мб
    1.14
    ل
    1.13
    POSITIVE LOGITS
     I
    1.23
     A
    1.20
     D
    1.06
     R
    0.96
     V
    0.96
    an
    0.95
     P
    0.95
     L
    0.95
     S
    0.94
     F
    0.90
    Activations Density 0.000%

    No Known Activations