© 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. 85193
    Prev
    Next
    INDEX
    Explanations

    ball control games and activities

    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
    っいて
    0.55
     computationally
    0.52
     рас
    0.52
     I
    0.52
    ların
    0.50
     immense
    0.50
    ano
    0.49
    ầ
    0.48
     беше
    0.48
    achy
    0.47
    POSITIVE LOGITS
    س
    0.78
    り
    0.70
    ग
    0.69
    د
    0.69
     glaciers
    0.68
    гры
    0.67
    êtres
    0.67
    organizzazione
    0.67
     setempat
    0.66
    ス
    0.66
    Activations Density 0.000%

    No Known Activations