© 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. 233156
    Prev
    Next
    INDEX
    Explanations

    gorgon, gorged, georgia, gorgeous

    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
    دی
    1.09
    và
    0.95
    きた
    0.92
    ↵
    0.89
    り
    0.85
     Bên
    0.84
    thed
    0.84
     سیا
    0.82
    και
    0.81
    casino
    0.81
    POSITIVE LOGITS
     at
    1.20
    s
    1.16
     as
    1.05
    ,
    1.00
     ont
    0.92
    us
    0.91
     o
    0.90
     astronomers
    0.90
     h
    0.89
     (
    0.89
    Activations Density 0.000%

    No Known Activations