© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74546
    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_31_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
     atac
    0.39
     polar
    0.36
     pere
    0.36
     prilikom
    0.36
     thoại
    0.35
     Peripheral
    0.35
     سارے
    0.34
     InputMaybe
    0.34
     美
    0.34
     tid
    0.34
    POSITIVE LOGITS
    <=
    0.39
    স্থলে
    0.37
    ssr
    0.37
     উচ্চ
    0.37
    昏
    0.36
     chiffres
    0.36
    昀
    0.36
    <?
    0.36
    ရင်း
    0.35
    lable
    0.35
    Activations Density 0.000%

    No Known Activations