© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133748
    Prev
    Next
    INDEX
    Explanations

    Basically

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    亿美元
    0.40
    蓬
    0.40
    ijs
    0.39
     রহমান
    0.38
    рец
    0.38
    ثمان
    0.35
    万美元
    0.35
    玉
    0.34
    棿
    0.34
     dólares
    0.34
    POSITIVE LOGITS
    ounters
    0.52
    anteen
    0.50
    ourt
    0.49
    utive
    0.48
    uerpo
    0.47
    atelli
    0.46
    clesiastical
    0.45
    rypto
    0.45
    ulture
    0.44
    riminating
    0.43
    Activations Density 0.002%

    No Known Activations