© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238570
    Prev
    Next
    INDEX
    Explanations

    Jews were often barred

    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_32_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
    差异
    0.39
    chemist
    0.39
    ramine
    0.38
    ին
    0.38
    வின
    0.38
    𝖑
    0.38
     england
    0.36
    BUILD
    0.36
    lycer
    0.36
    බ
    0.36
    POSITIVE LOGITS
     cong
    0.42
     fuc
    0.39
     puch
    0.38
     organizing
    0.37
     periphery
    0.37
     functions
    0.37
     adqu
    0.36
     gend
    0.36
     eyelids
    0.36
     pho
    0.35
    Activations Density 0.004%

    No Known Activations