© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 106834
    Prev
    Next
    INDEX
    Explanations

    kosher

    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_2_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
    ل
    1.72
    ح
    1.65
    ع
    1.42
    ა
    1.39
    م
    1.38
     to
    1.36
     or
    1.36
     It
    1.22
    를
    1.22
    us
    1.21
    POSITIVE LOGITS
    ći
    1.20
    n
    1.11
     encont
    1.03
    ков
    0.99
     Tattha
    0.97
     xmas
    0.97
    น
    0.97
    nina
    0.97
    ncia
    0.94
    𝓛
    0.93
    Activations Density 0.000%

    No Known Activations