© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197864
    Prev
    Next
    INDEX
    Explanations

    bridge and its failures

    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_12_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
    始める
    0.51
     사람들
    0.50
     років
    0.49
     жінок
    0.49
     চলা
    0.48
    ભાઇ
    0.48
     regenerating
    0.47
     vuoden
    0.46
    uhà
    0.46
    밍
    0.46
    POSITIVE LOGITS
     Bloem
    0.55
     Asha
    0.52
    %",
    0.50
     consigo
    0.50
    στα
    0.50
     Handwriting
    0.50
     Ecommerce
    0.50
     Antwerp
    0.49
    >+</
    0.49
     Indien
    0.49
    Activations Density 0.000%

    No Known Activations