© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121132
    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_37_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
     :)
    0.42
    引
    0.39
     Zone
    0.37
    chrane
    0.36
    恿
    0.35
     зарабо
    0.35
     Dollars
    0.35
    бо
    0.35
    telefon
    0.35
     zindagi
    0.34
    POSITIVE LOGITS
    ectin
    0.42
    、“
    0.41
     الدرس
    0.40
    荃
    0.39
     للس
    0.39
    scissor
    0.38
     JAN
    0.38
     passa
    0.38
    સ્તા
    0.38
    +=
    0.38
    Activations Density 0.000%

    No Known Activations