© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66250
    Prev
    Next
    INDEX
    Explanations

    car or vehicle locations

    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_41_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
    蛤
    0.46
    ɬ
    0.42
    ingt
    0.39
    ႆ
    0.39
     Rental
    0.38
     contratar
    0.37
    Rent
    0.37
     Hire
    0.37
     piace
    0.37
    ွာ
    0.37
    POSITIVE LOGITS
     voiture
    0.83
     cars
    0.82
    车
    0.82
     автомобиля
    0.81
     автомобиль
    0.79
     자동차
    0.78
    車
    0.77
    车的
    0.76
     গাড়িতে
    0.75
     автомобі
    0.75
    Activations Density 0.008%

    No Known Activations