© 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. 206782
    Prev
    Next
    INDEX
    Explanations

    forgo or quit

    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
     otras
    0.79
     يت
    0.75
     enslaved
    0.75
     Во
    0.73
     požad
    0.72
    _
    0.71
    <unused1861>
    0.69
     То
    0.67
     Α
    0.66
    箓
    0.66
    POSITIVE LOGITS
    s
    1.20
    o
    1.16
    AL
    1.10
    .
    1.06
    -
    0.98
    OR
    0.95
    IN
    0.91
    ו
    0.91
    AT
    0.91
    AV
    0.91
    Activations Density 0.000%

    No Known Activations