© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59373
    Prev
    Next
    INDEX
    Explanations

    Cost of Goods Sold (COGS)

    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_11_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
    ribut
    0.61
    ంగ్
    0.57
    umumkan
    0.57
     વિશ્વ
    0.56
     Espíritu
    0.54
     Нов
    0.54
    дель
    0.53
    扫
    0.53
    赈
    0.52
     வண
    0.52
    POSITIVE LOGITS
    .。
    0.51
     aggressively
    0.50
     parlor
    0.50
     increases
    0.48
     optimizing
    0.48
    (
    0.47
     （
    0.47
    edly
    0.46
    pharm
    0.46
     stockno
    0.46
    Activations Density 0.000%

    No Known Activations