© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 37063
    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_50_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
    bildung
    0.39
     сім
    0.38
    Whi
    0.38
     Samen
    0.37
     Durchmesser
    0.37
    htu
    0.36
    bcc
    0.36
    bc
    0.36
    默默
    0.36
     )}$
    0.36
    POSITIVE LOGITS
     prič
    0.38
    किस्तानी
    0.38
     Recuper
    0.37
    INION
    0.36
    换
    0.36
     gunshot
    0.35
     GAP
    0.35
    iek
    0.35
     FE
    0.34
     Enhance
    0.34
    Activations Density 0.000%

    No Known Activations