© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260963
    Prev
    Next
    INDEX
    Explanations

    Ma followed by names or French

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    t
    1.06
     étoile
    0.98
    いた
    0.97
    其他
    0.96
    
    0.95
    т
    0.90
    璺
    0.87
    عي
    0.86
    ك
    0.85
     Су
    0.84
    POSITIVE LOGITS
    ,
    1.34
    ;
    1.30
     \
    1.20
    is
    1.10
    ER
    1.08
    -
    1.08
    as
    1.05
     ,
    1.03
    ната
    1.02
    า
    1.02
    Activations Density 0.000%

    No Known Activations