© 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. 67693
    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
     林
    0.42
     веке
    0.39
     সমাধি
    0.39
    订单
    0.38
     情
    0.38
     tinh
    0.38
    ElementException
    0.38
    叅
    0.37
    𝟏
    0.37
    بلغ
    0.36
    POSITIVE LOGITS
     shiny
    0.55
    shiny
    0.50
     Shiny
    0.49
     bif
    0.48
     Mega
    0.45
    Mega
    0.44
     mega
    0.42
    mega
    0.42
     enclosed
    0.41
     зао
    0.41
    Activations Density 0.001%

    No Known Activations