© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13511
    Prev
    Next
    INDEX
    Explanations

    USB connection

    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_13_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
    czaj
    0.61
    cz
    0.57
     FormGroup
    0.56
     Komfort
    0.55
    צו
    0.55
    Ⲑ
    0.55
     Dato
    0.54
    慳
    0.54
    štu
    0.54
     Along
    0.53
    POSITIVE LOGITS
     USB
    0.70
     use
    0.63
     network
    0.62
     external
    0.62
     usb
    0.61
     cables
    0.59
     water
    0.59
     t
    0.58
     te
    0.58
     table
    0.56
    Activations Density 0.053%

    No Known Activations