© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85373
    Prev
    Next
    INDEX
    Explanations

    Chinese food items and names

    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_3_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
    (“
    0.57
    psie
    0.56
     പൂർ
    0.56
    <0xBB>
    0.55
    ේ
    0.54
    -
    0.54
    有一個
    0.53
    aser
    0.53
    ले
    0.52
     dotycz
    0.52
    POSITIVE LOGITS
    ру
    0.71
    1
    0.66
     It
    0.66
    re
    0.60
    ри
    0.54
     Environ
    0.52
    ի
    0.52
    វេល
    0.52
    ı
    0.52
    province
    0.51
    Activations Density 0.000%

    No Known Activations