© 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. 205988
    Prev
    Next
    INDEX
    Explanations

    bike or motorcycle

    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
     driver
    0.49
    🚘
    0.49
     car
    0.48
     driv
    0.46
     supercar
    0.46
    司机
    0.45
     ड्राइविंग
    0.45
     자동차
    0.45
    的车
    0.45
    🚙
    0.45
    POSITIVE LOGITS
     bikes
    0.76
     bike
    0.71
     Bike
    0.68
     बाइक
    0.65
    バイク
    0.58
    bikes
    0.58
    Bike
    0.58
     ridden
    0.57
     Bik
    0.55
     riders
    0.54
    Activations Density 0.001%

    No Known Activations