© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62367
    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_41_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
    Short
    1.14
     Short
    1.09
     short
    1.09
     SHORT
    1.05
    short
    0.96
    短
    0.94
     शॉर्ट
    0.94
    SHORT
    0.86
     短
    0.77
     shortage
    0.77
    POSITIVE LOGITS
     drag
    0.54
     dragged
    0.47
     Drag
    0.47
    drag
    0.47
     dragging
    0.43
     drags
    0.43
     funny
    0.42
    Drag
    0.41
     дра
    0.41
    Dragged
    0.40
    Activations Density 0.000%

    No Known Activations