© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129538
    Prev
    Next
    INDEX
    Explanations

    a

    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_50_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
    čun
    0.36
    들이
    0.34
    ğan
    0.34
    तील
    0.31
     í
    0.30
    weise
    0.30
    ři
    0.29
    ť
    0.29
    ğı
    0.29
    čiau
    0.29
    POSITIVE LOGITS
     ...]
    0.35
     Galbraith
    0.31
    ლები
    0.30
    nel
    0.29
     setCurrent
    0.29
    সন
    0.29
     $>
    0.29
     invigor
    0.29
     $\%
    0.29
     आध्यात्म
    0.29
    Activations Density 0.069%

    No Known Activations