© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217192
    Prev
    Next
    INDEX
    Explanations

    distraction or diversion

    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_31_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
    蠡
    0.37
    Winner
    0.36
     联系
    0.36
    Seal
    0.35
    iolipin
    0.35
     Envoy
    0.35
     Staff
    0.34
    挑戰
    0.34
     Winner
    0.34
    
    0.34
    POSITIVE LOGITS
     distract
    1.02
     distraction
    1.00
     distracted
    0.96
     distractions
    0.91
     distracting
    0.91
     distra
    0.84
     diversion
    0.71
     diverted
    0.64
     preoccupied
    0.63
     diverting
    0.63
    Activations Density 0.046%

    No Known Activations