© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110442
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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_2_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
    ت
    0.93
     legitim
    0.91
    t
    0.91
     by
    0.88
     synchron
    0.86
    Ве
    0.86
    Р
    0.85
     as
    0.84
     playwright
    0.84
            
    0.82
    POSITIVE LOGITS
    า
    1.84
    ні
    1.48
    ным
    1.23
    ா
    1.23
    א
    1.23
    ле
    1.17
    ק
    1.17
    ক
    1.16
    ча
    1.14
    ik
    1.11
    Activations Density 0.000%

    No Known Activations