© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32066
    Prev
    Next
    INDEX
    Explanations

    conditional swap logic

    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
     seemingly
    0.39
    䘚
    0.39
     शारीरिक
    0.37
     sebenarnya
    0.36
     aparentemente
    0.36
     teachers
    0.35
    似乎
    0.35
    所谓
    0.35
     পক্ষে
    0.34
     Doc
    0.34
    POSITIVE LOGITS
    Trendy
    0.40
    Pattern
    0.35
    kD
    0.35
    lust
    0.35
     ч
    0.34
    Creat
    0.34
    chutz
    0.34
     keeping
    0.34
    Net
    0.34
    uvo
    0.34
    Activations Density 0.011%

    No Known Activations