© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197460
    Prev
    Next
    INDEX
    Explanations

    say "The"

    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_50_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
     pretty
    0.46
     Pretty
    0.43
    锻
    0.38
     Mechanical
    0.37
     Assim
    0.37
    pretty
    0.36
     hepin
    0.36
     Input
    0.36
    prett
    0.36
     Modifications
    0.36
    POSITIVE LOGITS
    Speed
    0.36
     coprime
    0.36
    Faster
    0.36
    ফান
    0.36
    円
    0.35
    th
    0.35
    Resolve
    0.35
    rasp
    0.35
     sucrose
    0.35
    Chick
    0.35
    Activations Density 0.013%

    No Known Activations