© 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. 33282
    Prev
    Next
    INDEX
    Explanations

    mais

    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
    ၂
    0.71
    会导致
    0.62
     categorize
    0.61
    ૨
    0.60
     disorganized
    0.58
     себе
    0.58
     са
    0.57
    ية
    0.57
     reprise
    0.57
    سبة
    0.56
    POSITIVE LOGITS
     Hillsborough
    0.64
     I
    0.63
    am
    0.61
     Inggris
    0.60
     Archaeology
    0.59
    лии
    0.56
     V
    0.55
     พ
    0.55
    दारी
    0.55
    '
    0.55
    Activations Density 0.002%

    No Known Activations