© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109415
    Prev
    Next
    INDEX
    Explanations

    CAIR, AC, air

    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_1_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
    r
    1.75
    ي
    1.62
    at
    1.52
    ла
    1.39
    i
    1.29
    л
    1.29
    ل
    1.27
    ре
    1.27
    in
    1.24
    त
    1.23
    POSITIVE LOGITS
    0
    1.20
     Choir
    1.09
     Authorities
    1.08
     Drums
    1.02
     Holds
    0.96
     Baths
    0.96
    菀
    0.95
    CT
    0.94
    Fluor
    0.94
     Boats
    0.93
    Activations Density 0.000%

    No Known Activations