© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165518
    Prev
    Next
    INDEX
    Explanations

    dimensionless number or impulse

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Muscles
    0.40
     embod
    0.40
    tasks
    0.38
    鉞
    0.38
    juvant
    0.37
     atividades
    0.37
    ებული
    0.36
     Treated
    0.36
    walls
    0.35
    |}{
    0.35
    POSITIVE LOGITS
    Diploma
    0.38
     архив
    0.38
     reports
    0.38
    ดัง
    0.38
    OpenJDK
    0.38
     شفاف
    0.38
    Archive
    0.37
     गीता
    0.37
    Dependency
    0.37
    :”
    0.37
    Activations Density 0.007%

    No Known Activations