© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4746
    Prev
    Next
    INDEX
    Explanations

    Ty followed by common suffixes

    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_39_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
    jaw
    0.39
     convex
    0.38
     cerrada
    0.38
    eev
    0.38
    convex
    0.37
     waistband
    0.37
    /'.$
    0.36
    確率
    0.35
    改编
    0.34
     alcoved
    0.34
    POSITIVE LOGITS
     trick
    0.35
     try
    0.34
     researchers
    0.33
     Micron
    0.33
    ानों
    0.33
     Ty
    0.33
    Symbol
    0.33
    Researchers
    0.33
     Suggested
    0.33
     Iy
    0.33
    Activations Density 0.007%

    No Known Activations