© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206390
    Prev
    Next
    INDEX
    Explanations

    under laws or regulations

    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
     kated
    0.41
     Purcell
    0.39
     Authorized
    0.38
     뉴
    0.37
     अग्रणी
    0.36
    ానిక
    0.36
     AUTHOR
    0.35
     মুসলমানদের
    0.35
     vendedor
    0.35
    สังคม
    0.35
    POSITIVE LOGITS
     મુજબ
    0.39
     menurut
    0.39
     wings
    0.38
    gem
    0.38
    hamming
    0.37
    妫
    0.37
     methotrexate
    0.36
     Machu
    0.36
     حسب
    0.35
     stone
    0.35
    Activations Density 0.001%

    No Known Activations