© 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. 102986
    Prev
    Next
    INDEX
    Explanations

    Jules, MS, Smith

    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
    ン
    1.41
    น
    1.41
    न
    1.39
    та
    1.27
    కు
    1.24
    은
    1.21
    ن
    1.20
     thể
    1.19
    ية
    1.18
    я
    1.18
    POSITIVE LOGITS
    t
    1.90
    i
    1.65
    h
    1.38
    ي
    1.28
    ０
    1.27
    l
    1.20
    ون
    1.15
    w
    1.14
    atk
    1.11
    uing
    1.09
    Activations Density 0.000%

    No Known Activations