© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63706
    Prev
    Next
    INDEX
    Explanations

    cars

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     soup
    0.39
    鋯
    0.37
    guo
    0.36
     lamps
    0.35
    সম্প্র
    0.35
     compliant
    0.35
    Tow
    0.35
     landing
    0.34
    iffen
    0.34
     rail
    0.34
    POSITIVE LOGITS
     car
    2.97
    車
    2.53
    车
    2.48
     cars
    2.39
    車の
    2.22
    车的
    2.13
    cars
    2.08
     कार
    2.05
    car
    2.05
     Cars
    2.00
    Activations Density 0.037%

    No Known Activations