© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 233127
    Prev
    Next
    INDEX
    Explanations

    reverie and reverent

    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_6_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
    ك
    1.00
    נ
    0.98
    都
    0.88
    将
    0.88
    家
    0.86
     impide
    0.86
    خ
    0.84
     to
    0.82
    {
    0.82
    ిన
    0.80
    POSITIVE LOGITS
    z
    1.25
    l
    1.20
    ó
    1.20
     L
    1.18
     Y
    1.16
    ur
    1.15
     N
    1.15
    ai
    1.14
    ana
    1.13
     H
    1.09
    Activations Density 0.000%

    No Known Activations