© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90334
    Prev
    Next
    INDEX
    Explanations

    emojis and 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_11_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
    akers
    0.55
     ultraviolet
    0.48
    ker
    0.48
    खास्त
    0.48
    ada
    0.46
    v
    0.46
     clés
    0.45
    
    0.45
     alan
    0.44
     Ultraviolet
    0.44
    POSITIVE LOGITS
    то
    0.50
    wk
    0.49
    этому
    0.46
    сив
    0.46
    ώς
    0.44
    Prz
    0.44
    треб
    0.44
    ทด
    0.43
    setStyleSheet
    0.43
     ск
    0.43
    Activations Density 0.002%

    No Known Activations