© 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. 1783
    Prev
    Next
    INDEX
    Explanations

    multilingual characters

    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
     Groundwater
    0.39
     lãi
    0.39
    үүн
    0.38
    libre
    0.38
    우
    0.37
     shrewd
    0.37
    ãi
    0.36
     nisid
    0.36
     groundwater
    0.36
     yǐ
    0.36
    POSITIVE LOGITS
     डब्ल्यू
    0.43
    圜
    0.40
     круг
    0.37
     স্টেট
    0.37
     Commit
    0.36
    eryka
    0.36
     Mast
    0.36
     elf
    0.36
     Hatch
    0.35
     पाउ
    0.35
    Activations Density 0.003%

    No Known Activations