© 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. 11522
    Prev
    Next
    INDEX
    Explanations

    Chinese, Russian, English, German, Turkish, Bengali, Malayalam, Ukrainian, philosophical concepts, legal terms

    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
     Leonard
    0.44
     Zacks
    0.43
     Tats
    0.41
     patriarch
    0.39
     McKinley
    0.39
    惯
    0.39
     trophies
    0.38
     accustomed
    0.38
     Leonardo
    0.38
     Abrams
    0.38
    POSITIVE LOGITS
     അതി
    0.46
    ницы
    0.45
     sayfası
    0.41
     ডাউন
    0.40
     डाउन
    0.38
    妞
    0.38
    arbeiten
    0.38
    httparty
    0.38
    Processed
    0.38
     পিঁপ
    0.37
    Activations Density 0.027%

    No Known Activations