© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120936
    Prev
    Next
    INDEX
    Explanations

    ASCII art or symbols

    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_27_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
    丰
    0.40
     త
    0.39
     تھی
    0.39
     devam
    0.37
     wh
    0.36
     Sole
    0.35
    豐
    0.34
     sẽ
    0.33
     temas
    0.33
    它们
    0.33
    POSITIVE LOGITS
    
    0.43
    ऑस्ट्रेलिया
    0.42
    
    0.41
    ❽
    0.40
    ❍
    0.40
    voltage
    0.39
    काउंट
    0.39
    ロマ
    0.39
    wavelength
    0.39
    '&
    0.38
    Activations Density 0.002%

    No Known Activations