© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213546
    Prev
    Next
    INDEX
    Explanations

    Thai phrases followed by punctuation

    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
    of
    1.91
    on
    1.59
    i
    1.48
    ли
    1.40
    ed
    1.37
    f
    1.34
    ي
    1.32
    ص
    1.29
    is
    1.28
    will
    1.27
    POSITIVE LOGITS
     a
    1.11
    ↵
    1.04
    ید
    1.04
        
    1.02
    에
    1.02
     apresent
    1.01
            
    1.00
     it
    0.99
    im
    0.98
     hospitable
    0.96
    Activations Density 0.000%

    No Known Activations