© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90309
    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_23_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
     dunque
    0.14
     Louis
    0.13
     pozn
    0.13
     Именно
    0.13
     പൂർ
    0.13
     Ρ
    0.13
     Тар
    0.13
     blond
    0.13
     Valerie
    0.13
    ন্স
    0.13
    POSITIVE LOGITS
    брь
    0.15
    等待
    0.13
    ver
    0.13
     Yucatan
    0.13
    unggu
    0.13
    Buenos
    0.13
    Healing
    0.13
    타
    0.13
     стрельца
    0.13
    FCO
    0.13
    Activations Density 0.000%

    No Known Activations