© 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. 149717
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     figuring
    0.43
     from
    0.42
     in
    0.41
     refle
    0.40
     burning
    0.39
     appli
    0.39
     or
    0.39
     ಜೆ
    0.38
     compos
    0.38
     Е
    0.37
    POSITIVE LOGITS
    brand
    0.42
    pulse
    0.40
     ,
    0.38
    <strong>
    0.38
    haven
    0.38
    spirit
    0.37
    chamber
    0.37
    material
    0.37
    bandits
    0.37
    staaten
    0.37
    Activations Density 0.000%

    No Known Activations