© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192510
    Prev
    Next
    INDEX
    Explanations

    is / is-

    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_4_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
    1.43
    น
    1.34
    도
    1.32
    し
    1.30
    在
    1.30
    ب
    1.27
    ления
    1.23
    ление
    1.17
    Ρ
    1.16
     in
    1.13
    POSITIVE LOGITS
    1.43
    ן
    1.10
    ur
    0.99
    gou
    0.82
     a
    0.81
     अपना
    0.81
     i
    0.80
    ků
    0.80
     thách
    0.80
    oi
    0.79
    Activations Density 0.005%

    No Known Activations