© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69495
    Prev
    Next
    INDEX
    Explanations

    workshop

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     couch
    0.46
    旄
    0.44
    Tucker
    0.43
    सिले
    0.42
     Couch
    0.40
    couch
    0.39
     Tucker
    0.38
     仕
    0.38
     Lynch
    0.37
    溲
    0.37
    POSITIVE LOGITS
     workshop
    2.67
     workshops
    2.61
    Workshop
    2.56
     Workshops
    2.55
     Workshop
    2.53
    workshop
    2.48
     talleres
    1.83
     ateliers
    1.43
    atelier
    1.10
     atelier
    1.09
    Activations Density 0.025%

    No Known Activations