© 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. 195565
    Prev
    Next
    INDEX
    Explanations

    wheeled vehicles

    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
     car
    0.80
    车
    0.68
     कार
    0.66
    車
    0.65
    car
    0.64
     cars
    0.62
     Car
    0.57
     Cars
    0.57
    的车
    0.57
    Cars
    0.55
    POSITIVE LOGITS
    伊
    0.39
    юро
    0.38
     Königs
    0.37
     gain
    0.36
     affair
    0.36
     homer
    0.36
     iga
    0.36
     cuộc
    0.36
     Ubuy
    0.36
    Ⲟ
    0.36
    Activations Density 0.001%

    No Known Activations