© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53508
    Prev
    Next
    INDEX
    Explanations

    MBTA 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_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
    捎
    0.39
    Ra
    0.39
    addChild
    0.38
    бак
    0.38
     Ra
    0.37
     handicap
    0.37
     poisons
    0.37
    ounters
    0.37
     Adverse
    0.37
     dives
    0.37
    POSITIVE LOGITS
     '';
    0.37
    activated
    0.37
     activate
    0.37
    不知
    0.35
     `#
    0.34
     অতিক্রম
    0.33
     расти
    0.33
    ethane
    0.33
    जलवायु
    0.32
     маши
    0.32
    Activations Density 0.009%

    No Known Activations