© 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. 9760
    Prev
    Next
    INDEX
    Explanations

    retail, shopping, malls, shops

    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
    0
    0.53
    WE
    0.47
    وك
    0.46
    قع
    0.45
    <em>
    0.45
    <thead>
    0.45
    ول
    0.45
    冈
    0.45
    he
    0.44
    we
    0.44
    POSITIVE LOGITS
    零售
    0.64
     malls
    0.63
     alış
    0.59
     florist
    0.58
     दुकानों
    0.56
     retailers
    0.55
     магази
    0.55
     දැ
    0.55
     lojas
    0.55
     shoppers
    0.54
    Activations Density 0.033%

    No Known Activations