© 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. 103084
    Prev
    Next
    INDEX
    Explanations

    basque or turkish language

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ם
    1.47
    is
    1.45
    ,
    1.41
    in
    1.38
    on
    1.34
    هم
    1.30
    ue
    1.28
    at
    1.26
    ز
    1.25
    ام
    1.20
    POSITIVE LOGITS
    ા
    1.48
    a
    1.36
    া
    1.36
    า
    1.21
    ା
    1.16
    ﻜ
    1.15
     Yên
    1.12
    ați
    1.12
     élargies
    1.09
    
    1.09
    Activations Density 0.003%

    No Known Activations