© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74577
    Prev
    Next
    INDEX
    Explanations

    pre-existing conditions and vulnerabilities

    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_31_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
     Palo
    0.37
     Leop
    0.33
     Auditorium
    0.32
     oranges
    0.31
    calo
    0.30
    拿
    0.30
    indo
    0.29
     palo
    0.29
    agam
    0.29
    ផ្ស
    0.29
    POSITIVE LOGITS
     Disabilities
    0.39
    奴
    0.33
     Barriers
    0.31
     समायोजित
    0.31
     []*
    0.31
     impl
    0.30
    ثم
    0.30
     disabilities
    0.30
     Immediate
    0.30
     ziek
    0.29
    Activations Density 0.007%

    No Known Activations