© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46965
    Prev
    Next
    INDEX
    Explanations

    CAN bus communication

    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_3_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
    ä
    0.76
    мм
    0.75
    I
    0.72
    ні
    0.70
    are
    0.69
    that
    0.68
    ans
    0.67
    aircraft
    0.67
    ons
    0.67
    ۹
    0.66
    POSITIVE LOGITS
    ك
    0.83
     إن
    0.70
     impecc
    0.67
     regroup
    0.67
     insign
    0.67
     ودي
    0.67
     على
    0.66
     ولي
    0.65
     insegn
    0.65
     أب
    0.64
    Activations Density 0.003%

    No Known Activations