© 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. 199620
    Prev
    Next
    INDEX
    Explanations

    Chinese words and names

    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
    Ap
    0.46
    Erik
    0.42
     Forester
    0.40
    Ellen
    0.39
    Pra
    0.38
    子
    0.38
    App
    0.37
    ocot
    0.37
    사장
    0.37
     Erik
    0.37
    POSITIVE LOGITS
     Feng
    0.42
    亢
    0.39
     मैती
    0.39
     Genoa
    0.39
    enty
    0.38
    engk
    0.38
     উৎ
    0.38
    atok
    0.38
    ylem
    0.37
    tdd
    0.37
    Activations Density 0.007%

    No Known Activations