© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48247
    Prev
    Next
    INDEX
    Explanations

    performance and decision analysis

    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_31_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
    研究
    0.39
     연구
    0.37
     research
    0.36
    upy
    0.34
    贸易
    0.33
    分类
    0.33
    应用
    0.32
    找
    0.32
    关
    0.32
     అధ్య
    0.31
    POSITIVE LOGITS
     قص
    0.40
    Past
    0.39
    Donor
    0.38
     Seafood
    0.38
    Assess
    0.37
     episodios
    0.37
    Personal
    0.36
    Target
    0.35
    Diabetes
    0.35
     sashimi
    0.34
    Activations Density 0.013%

    No Known Activations