© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121773
    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_27_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
     benthic
    0.46
     coyote
    0.44
     diatom
    0.44
     plantar
    0.43
     filtration
    0.43
     crayfish
    0.43
    😏
    0.43
     monkey
    0.43
    𝘆
    0.43
     visc
    0.42
    POSITIVE LOGITS
     Econ
    0.43
    ukul
    0.39
     بدی
    0.37
     Interess
    0.36
     главного
    0.36
    тру
    0.36
     மே
    0.35
     учеб
    0.34
     ஆண்டில்
    0.34
     економі
    0.34
    Activations Density 0.000%

    No Known Activations