© 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. 238543
    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
    畨
    0.40
    కర
    0.39
    য়াল
    0.39
     الفي
    0.38
    แมนเชสเตอร์ซิตี
    0.37
     Rxa
    0.37
    㫧
    0.36
     கலந்து
    0.35
    ҕ
    0.35
    makeText
    0.35
    POSITIVE LOGITS
     commercially
    0.42
    মিও
    0.40
     sanity
    0.39
     Commercial
    0.38
     COMMERCIAL
    0.38
    commercial
    0.38
    highly
    0.38
     পরীক্ষ
    0.37
    ությ
    0.37
     protege
    0.37
    Activations Density 0.000%

    No Known Activations