© 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. 143617
    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_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
     Janeiro
    0.44
     Δεν
    0.42
     consecutively
    0.41
     შეუ
    0.41
    拍卖
    0.39
     सिलसिले
    0.39
     morceaux
    0.38
    кана
    0.38
     Forget
    0.38
    𝑑
    0.38
    POSITIVE LOGITS
    ATR
    0.39
     serious
    0.38
    bir
    0.35
    MAIL
    0.35
     panel
    0.35
     Panel
    0.35
     panelists
    0.34
     seriously
    0.34
     "-//
    0.34
    etar
    0.34
    Activations Density 0.000%

    No Known Activations