© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202958
    Prev
    Next
    INDEX
    Explanations

    maintenance and downtime scheduling

    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_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flash
    0.53
     lobster
    0.49
      
    0.49
     firearm
    0.48
    ’
    0.47
    response
    0.47
    ire
    0.47
    ale
    0.46
    ere
    0.46
     cybersecurity
    0.46
    POSITIVE LOGITS
     где
    0.57
     проведения
    0.57
    ləşdir
    0.56
    专题
    0.55
    [\
    0.53
     shutdowns
    0.52
    皘
    0.52
    ి
    0.52
    არი
    0.50
     infliction
    0.50
    Activations Density 0.039%

    No Known Activations