© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102968
    Prev
    Next
    INDEX
    Explanations

    enforcement

    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_1_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
    h
    1.90
    l
    1.73
    d
    1.70
    n
    1.67
    g
    1.49
    z
    1.46
    m
    1.39
    t
    1.35
    v
    1.32
    ek
    1.30
    POSITIVE LOGITS
    in
    1.68
    もの
    1.41
    ی
    1.33
    been
    1.27
     be
    1.26
    ۔
    1.26
    inę
    1.24
    は
    1.24
    inį
    1.23
    는
    1.22
    Activations Density 0.001%

    No Known Activations