© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205270
    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_10_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
     físico
    0.50
    ب
    0.48
    ین
    0.48
    తో
    0.48
    ات
    0.47
     cát
    0.47
    に含ま
    0.47
    肐
    0.46
     класси
    0.46
    ב
    0.45
    POSITIVE LOGITS
     by
    0.64
     Lane
    0.50
    겼
    0.49
     Weiß
    0.49
     approached
    0.48
     Latino
    0.48
     been
    0.47
     Version
    0.47
     Über
    0.46
     overly
    0.46
    Activations Density 0.000%

    No Known Activations