© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26666
    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_40_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
    傳
    0.48
    传
    0.44
    伝
    0.44
     Tobin
    0.43
     खिच
    0.42
    اران
    0.41
     quartic
    0.40
     fewest
    0.40
    requently
    0.40
    鏝
    0.40
    POSITIVE LOGITS
    Health
    0.39
    head
    0.39
    chelles
    0.37
    વેશ
    0.36
    umes
    0.36
    elemento
    0.35
    分解
    0.35
    Pand
    0.34
    avis
    0.33
    health
    0.33
    Activations Density 0.001%

    No Known Activations