© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136108
    Prev
    Next
    INDEX
    Explanations

    wreck, wreckage, Mater, breaks

    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_12_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
     conceded
    0.53
     Recursos
    0.48
    ك
    0.47
    قيم
    0.47
     consiguió
    0.47
     conseguir
    0.46
    ودي
    0.43
    اني
    0.43
     conceding
    0.43
    ણે
    0.42
    POSITIVE LOGITS
    $
    0.44
    Pat
    0.42
     meny
    0.42
    |<\
    0.42
    $-
    0.41
    [\
    0.41
     एवरी
    0.41
     वाढ
    0.40
     tattha
    0.40
    Nothing
    0.40
    Activations Density 0.001%

    No Known Activations