© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93987
    Prev
    Next
    INDEX
    Explanations

    for (various languages)

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     ră
    0.45
    ără
    0.45
    p
    0.40
    că
    0.39
     kamera
    0.37
    лиза
    0.37
    ătă
    0.37
    ៨
    0.37
    قد
    0.36
    [
    0.35
    POSITIVE LOGITS
     for
    1.31
     voor
    0.82
     For
    0.81
    For
    0.75
    for
    0.73
     για
    0.70
     برای
    0.68
     FOR
    0.64
     für
    0.64
     для
    0.63
    Activations Density 0.000%

    No Known Activations