© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43973
    Prev
    Next
    INDEX
    Explanations

    salt, pepper, spice, bay

    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
    ร์
    0.58
     che
    0.56
    트에
    0.55
         
    0.55
     قیمت
    0.53
     scelto
    0.53
     ito
    0.53
    ₪
    0.52
    ції
    0.52
    ตรา
    0.52
    POSITIVE LOGITS
     पीपल
    0.52
     epoxide
    0.49
     woody
    0.48
     ఆల
    0.48
    FileDialog
    0.47
    आरटी
    0.47
    PJ
    0.47
    ewood
    0.47
     गोला
    0.47
     fooling
    0.47
    Activations Density 0.014%

    No Known Activations