© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84913
    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_0_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
     set
    0.55
    j
    0.52
    l
    0.51
     s
    0.50
    n
    0.50
    綿
    0.49
     you
    0.48
     south
    0.48
    ર
    0.48
     there
    0.48
    POSITIVE LOGITS
    макраты
    0.60
     توز
    0.53
    PGS
    0.51
     envolvendo
    0.51
     реально
    0.50
     노트북
    0.48
    жала
    0.48
     kvadr
    0.48
     jakieś
    0.48
     význam
    0.48
    Activations Density 0.000%

    No Known Activations