© 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. 156469
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    你
    1.53
    我们
    1.51
    我
    1.38
    پ
    1.21
    .
    1.19
    คุณ
    1.16
     поги
    1.05
     возмо
    1.04
    प
    1.04
    श
    1.03
    POSITIVE LOGITS
    in
    1.30
    el
    1.29
    ul
    1.11
    ן
    0.97
    에
    0.95
    च्या
    0.93
    FQ
    0.92
    Foe
    0.86
    ០
    0.86
    um
    0.85
    Activations Density 0.000%

    No Known Activations