© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 209762
    Prev
    Next
    INDEX
    Explanations

    reflex

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
    䪲
    0.43
    enderita
    0.40
    ื้อง
    0.38
    динку
    0.37
     रीजन
    0.37
     Declar
    0.37
    idoscope
    0.37
    自治
    0.36
     Conflicts
    0.36
    噢
    0.36
    POSITIVE LOGITS
     ring
    0.37
     sót
    0.37
     honorable
    0.37
    ringen
    0.36
    环
    0.36
     रिंग
    0.36
    rels
    0.35
    OrFail
    0.35
     defensive
    0.35
     slow
    0.34
    Activations Density 0.001%

    No Known Activations