© 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. 47310
    Prev
    Next
    INDEX
    Explanations

    American College of

    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
    ječ
    0.54
     účast
    0.52
    خصة
    0.51
    ේ
    0.51
    ňuje
    0.50
     slučaju
    0.50
    ană
    0.49
     Parmi
    0.49
     دين
    0.48
     Malgré
    0.48
    POSITIVE LOGITS
    س
    0.80
    I
    0.72
    V
    0.66
    아
    0.65
    О
    0.64
    H
    0.63
    До
    0.63
    ΙΚ
    0.62
    एस
    0.61
     ampli
    0.61
    Activations Density 0.001%

    No Known Activations