© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123405
    Prev
    Next
    INDEX
    Explanations

    compare-exchange operations

    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_37_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
     сала
    0.43
     diversify
    0.40
     adhes
    0.39
    POL
    0.38
     Pitch
    0.37
    鲵
    0.37
    ডিও
    0.36
     Quarter
    0.35
     pitching
    0.35
    輋
    0.35
    POSITIVE LOGITS
     交換
    0.43
     जातीय
    0.42
    swap
    0.40
     የም
    0.40
     swap
    0.40
     Comparing
    0.38
     COMPARE
    0.38
    cmt
    0.37
     अनन्या
    0.37
    交換
    0.37
    Activations Density 0.000%

    No Known Activations