© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78157
    Prev
    Next
    INDEX
    Explanations

    directory traversal sequences

    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_0_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
    s
    2.44
     =
    1.77
     (
    1.70
    data
    1.62
     as
    1.57
     have
    1.52
    g
    1.45
    token
    1.41
    daki
    1.41
    type
    1.39
    POSITIVE LOGITS
    م
    2.73
    ल
    2.22
    ب
    1.76
    ו
    1.62
    ম
    1.61
    й
    1.59
    <0x0D>
    1.51
    ל
    1.48
    מ
    1.48
    ज
    1.46
    Activations Density 0.000%

    No Known Activations