© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 29916
    Prev
    Next
    INDEX
    Explanations

    barrels

    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_7_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
     the
    1.27
     in
    1.21
    ↵
    1.16
    the
    1.16
    و
    1.09
    י
    1.05
     marine
    0.98
     divine
    0.91
    is
    0.91
     can
    0.90
    POSITIVE LOGITS
    na
    0.96
    on
    0.95
    １
    0.93
    noz
    0.92
     ouvrir
    0.91
     efectuar
    0.91
     ၁
    0.90
    ngr
    0.89
     postures
    0.89
     HTMLSc
    0.89
    Activations Density 0.001%

    No Known Activations