© 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. 133876
    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
    स्व
    0.40
    Cult
    0.40
    anées
    0.39
    usnya
    0.38
    Proofs
    0.38
     অর্ডার
    0.38
    paysys
    0.38
    ቴ
    0.37
     провин
    0.36
    anediyl
    0.36
    POSITIVE LOGITS
     Outcome
    0.45
     outcome
    0.37
    扨
    0.36
    ాన్ని
    0.35
     smel
    0.34
     Maker
    0.34
     måle
    0.34
     materia
    0.33
     materially
    0.33
     εργ
    0.33
    Activations Density 0.000%

    No Known Activations