© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67690
    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_41_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
     uncon
    0.42
     Samson
    0.41
    combine
    0.39
     COURSE
    0.39
    તાવ
    0.39
     Un
    0.39
     Course
    0.38
    歆
    0.38
     combine
    0.37
     course
    0.36
    POSITIVE LOGITS
    dial
    0.44
     భాష
    0.42
    ภาษา
    0.42
     dial
    0.41
     dialect
    0.41
     language
    0.40
    Dial
    0.40
    languages
    0.39
    wab
    0.39
     nyelv
    0.39
    Activations Density 0.000%

    No Known Activations