© 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. 194738
    Prev
    Next
    INDEX
    Explanations

    grammar

    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
     whale
    0.43
    𝔂
    0.38
     whales
    0.38
    اث
    0.37
    нија
    0.36
     hatch
    0.36
    јо
    0.36
    ιε
    0.36
     travelling
    0.36
    ይታ
    0.36
    POSITIVE LOGITS
    ADOC
    0.39
     cognitiva
    0.39
    antlr
    0.39
    plasm
    0.38
     Copeland
    0.37
    捩
    0.37
     डब्ल्यू
    0.36
     ಕಡಿಮೆ
    0.35
     finalist
    0.35
    oxygenase
    0.35
    Activations Density 0.000%

    No Known Activations