© 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. 165588
    Prev
    Next
    INDEX
    Explanations

    swapping elements or characters

    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
    增加
    0.47
    ɡ
    0.40
     newNode
    0.39
     Ngh
    0.38
     Lua
    0.37
    娥
    0.37
     साम
    0.36
     jong
    0.36
    ambahan
    0.36
    櫚
    0.36
    POSITIVE LOGITS
     boiler
    0.38
    Naz
    0.38
    equipped
    0.35
     adventure
    0.34
    㘟
    0.34
    лосо
    0.34
    boiler
    0.34
     SS
    0.34
     creativo
    0.34
    スピ
    0.33
    Activations Density 0.001%

    No Known Activations