© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8781
    Prev
    Next
    INDEX
    Explanations

    journal articles

    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_13_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
     océano
    0.55
     tipo
    0.51
    ີ້
    0.50
     tipe
    0.49
     protezione
    0.49
     memorize
    0.48
     ích
    0.48
     ụ
    0.47
    К
    0.47
    海水
    0.47
    POSITIVE LOGITS
    atov
    0.46
    ник
    0.43
     Slug
    0.42
    slug
    0.41
    rill
    0.41
    onent
    0.41
    asher
    0.41
     그러면
    0.41
     will
    0.40
     Demp
    0.39
    Activations Density 0.009%

    No Known Activations