© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1854
    Prev
    Next
    INDEX
    Explanations

    specific events

    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_44_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
    至于
    0.38
    apiro
    0.38
     spill
    0.37
    兵
    0.37
     srebr
    0.36
    ibor
    0.36
    ኖ
    0.36
     Rott
    0.36
    Researcher
    0.36
     Nep
    0.36
    POSITIVE LOGITS
    駈
    0.38
    []}
    0.37
     inspirational
    0.36
     ศูนย์
    0.35
     rif
    0.34
     Бе
    0.34
    磊
    0.34
     પહે
    0.33
     vagu
    0.33
     chauffeur
    0.33
    Activations Density 0.013%

    No Known Activations