© 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. 31897
    Prev
    Next
    INDEX
    Explanations

    Japan

    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
    crs
    0.39
    ク
    0.39
    ｸ
    0.38
    ҳи
    0.37
    鿓
    0.37
    㧡
    0.37
    nbhost
    0.37
    𝑓
    0.36
    んにちは
    0.36
    秶
    0.36
    POSITIVE LOGITS
     moyenne
    0.42
     термина
    0.41
     recv
    0.41
     Roder
    0.41
     Е
    0.40
     surf
    0.40
     receiver
    0.40
    менение
    0.39
     Fits
    0.38
     chainsaw
    0.38
    Activations Density 0.000%

    No Known Activations