© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10280
    Prev
    Next
    INDEX
    Explanations

    automotive aftermarket parts and racing

    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_40_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
    楫
    0.39
     पड़
    0.38
    ,]
    0.38
     bunker
    0.37
     renunci
    0.36
    cream
    0.36
    鈉
    0.36
    ច
    0.35
    ഗോ
    0.35
    Credit
    0.34
    POSITIVE LOGITS
     aftermarket
    0.73
    Parts
    0.69
     PARTS
    0.68
     racing
    0.66
     parts
    0.65
     Teile
    0.65
     Parts
    0.64
    parts
    0.62
     Motorsports
    0.61
     Racing
    0.61
    Activations Density 0.031%

    No Known Activations