© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121751
    Prev
    Next
    INDEX
    Explanations

    render or server configuration

    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_38_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
     shark
    1.09
     sharks
    1.01
    Shark
    0.99
     Shark
    0.97
    shark
    0.93
    🦈
    0.86
     Sharks
    0.82
    鮫
    0.77
    鯊
    0.73
    鲨
    0.70
    POSITIVE LOGITS
    Fraud
    0.43
     Kik
    0.41
     Societies
    0.39
     граждан
    0.37
     Disbursements
    0.37
    Canada
    0.37
    ociety
    0.36
    riteria
    0.35
     בג
    0.35
    Constr
    0.35
    Activations Density 0.009%

    No Known Activations