© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125618
    Prev
    Next
    INDEX
    Explanations

    talking about teams

    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_37_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
     fan
    2.03
     fans
    1.95
     팬
    1.86
    Fan
    1.78
    Fans
    1.77
     Fans
    1.76
     Fan
    1.72
     fandom
    1.70
    팬
    1.69
     फैन
    1.66
    POSITIVE LOGITS
    Recipe
    0.38
     دیتا
    0.37
     vapeur
    0.37
     Drone
    0.36
    攣
    0.36
    лән
    0.35
    synth
    0.35
     Sessions
    0.35
    麴
    0.34
     drones
    0.34
    Activations Density 0.013%

    No Known Activations