© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154692
    Prev
    Next
    INDEX
    Explanations

    merchants

    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
    赜
    0.40
     ইন্দিরা
    0.40
    리카
    0.39
    酪
    0.38
    వె
    0.37
     Rainbow
    0.37
     প্লা
    0.36
    FH
    0.36
     स्टूडियो
    0.36
     ट्राई
    0.35
    POSITIVE LOGITS
     merchant
    2.98
     Merchant
    2.89
    Merchant
    2.77
    merchant
    2.75
     merchants
    2.63
     Merchants
    2.55
     MERCHANT
    2.53
    商
    1.73
    商人
    1.71
    商家
    1.52
    Activations Density 0.000%

    No Known Activations