© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96432
    Prev
    Next
    INDEX
    Explanations

    fender and hull

    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_14_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
    ChooseCharacter
    0.67
     アー
    0.63
    źdz
    0.62
     То
    0.61
    ታዊ
    0.59
    geschossiges
    0.58
    ProductsStore
    0.58
     Пра
    0.57
    чий
    0.57
    Ꮬ
    0.56
    POSITIVE LOGITS
     genus
    0.57
     curbing
    0.56
    t
    0.53
     gold
    0.52
    ながら
    0.52
     kilowatt
    0.52
     amel
    0.50
    ed
    0.50
     I
    0.49
     kitap
    0.49
    Activations Density 0.000%

    No Known Activations