© 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. 238535
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ด้วย
    0.41
     চেয়ার
    0.39
     Sort
    0.38
    щего
    0.38
     নও
    0.36
    Availability
    0.36
    教室
    0.36
    CSE
    0.35
    以
    0.35
    不但
    0.35
    POSITIVE LOGITS
     during
    0.38
     skier
    0.37
    プロフィール
    0.37
    clair
    0.37
     протяжении
    0.36
     максима
    0.36
     durant
    0.36
     convict
    0.36
    零售
    0.36
     apasion
    0.35
    Activations Density 0.000%

    No Known Activations