© 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. 121211
    Prev
    Next
    INDEX
    Explanations

    SQL course

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    bury
    0.40
     endoscopy
    0.38
    最小
    0.38
     बिजनेस
    0.38
     све
    0.37
    hoa
    0.36
    䏹
    0.36
    mmas
    0.35
    राष्ट्र
    0.35
    све
    0.35
    POSITIVE LOGITS
    otum
    0.42
     boutons
    0.39
     color
    0.38
     botones
    0.38
     monter
    0.38
     सरा
    0.38
     illustration
    0.37
     करतात
    0.37
    .}(
    0.36
     Avner
    0.36
    Activations Density 0.000%

    No Known Activations