© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 835
    Prev
    Next
    INDEX
    Explanations

    retired, former, worked

    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_39_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
     neglected
    0.43
     neglect
    0.38
     ಮನೆ
    0.37
     négl
    0.35
    ateri
    0.33
     ಹೆಸರು
    0.33
    Ꭷ
    0.33
    arel
    0.33
    ред
    0.32
     হাসপাতাল
    0.31
    POSITIVE LOGITS
     ай
    0.42
     Override
    0.38
     아이
    0.37
    추
    0.37
     tempo
    0.37
     iOS
    0.37
     entrar
    0.37
     abra
    0.37
     сви
    0.37
     recevoir
    0.36
    Activations Density 0.004%

    No Known Activations