© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32673
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     заря
    0.42
    Ꭶ
    0.39
     Definitions
    0.39
    Frederick
    0.38
     ലോ
    0.38
    Según
    0.38
     điện
    0.37
     Cádiz
    0.37
    鑄
    0.37
    䂧
    0.37
    POSITIVE LOGITS
     lack
    0.50
     Lack
    0.48
    Lack
    0.48
     lacks
    0.46
     lacking
    0.46
     manque
    0.45
    lack
    0.42
     mancanza
    0.41
    缺乏
    0.41
     lacked
    0.40
    Activations Density 0.018%

    No Known Activations