© 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. 205231
    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
     ändern
    0.56
    u
    0.52
    ð
    0.49
    ise
    0.47
    龵
    0.47
    är
    0.46
    se
    0.45
     réussite
    0.45
     möglich
    0.45
     mindestens
    0.45
    POSITIVE LOGITS
    ્ષ
    0.62
     Mili
    0.54
    น
    0.54
     દ્વારા
    0.53
    チャ
    0.51
    飾り
    0.50
     በሽታ
    0.50
    оло
    0.50
    ुलिस
    0.49
    ビリ
    0.49
    Activations Density 0.000%

    No Known Activations