© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13664
    Prev
    Next
    INDEX
    Explanations

    costs, productivity, sales, failures

    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_40_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
    캥
    0.43
     Qar
    0.41
     मं
    0.39
    EVENT
    0.39
    模型
    0.38
    qus
    0.38
     моделей
    0.37
     बहू
    0.36
     mouseDown
    0.36
    Q
    0.36
    POSITIVE LOGITS
     scrap
    0.65
     Scrap
    0.51
     scrapped
    0.50
    Forecast
    0.45
     scraps
    0.44
    scrap
    0.44
     schedules
    0.42
     scrapping
    0.42
     defect
    0.41
     stok
    0.41
    Activations Density 0.084%

    No Known Activations