© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40578
    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_57_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
    Hib
    0.48
    otre
    0.46
    擷
    0.42
     Hib
    0.41
    inkler
    0.40
    ೊಂಡ
    0.39
     Era
    0.38
    transport
    0.38
    備
    0.38
    hib
    0.38
    POSITIVE LOGITS
     Verdun
    0.41
    ास
    0.36
    ព
    0.36
     EDWARD
    0.36
     ss
    0.35
    adoo
    0.35
     создан
    0.35
     BUREAU
    0.34
    OnHand
    0.34
     Buren
    0.34
    Activations Density 0.000%

    No Known Activations