© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 62949
    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_46_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
     categorias
    0.39
    ưng
    0.38
     MainPage
    0.37
    卢
    0.37
    lus
    0.37
     JOHN
    0.36
     sv
    0.36
     AREAS
    0.36
    ologia
    0.36
     Svens
    0.36
    POSITIVE LOGITS
    ራም
    0.40
    ZUKI
    0.39
     trasp
    0.38
    ={[
    0.37
    ネイ
    0.36
     Spinal
    0.35
    🐍
    0.35
    Supplement
    0.35
    ску
    0.35
     ছুই
    0.35
    Activations Density 0.000%

    No Known Activations