© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140706
    Prev
    Next
    INDEX
    Explanations

    South China Sea

    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_12_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
     Record
    0.54
     Work
    0.49
     กลุ่ม
    0.48
    К
    0.48
    下的
    0.48
    边
    0.47
     सदस्य
    0.47
    లిన
    0.47
    лери
    0.46
    廉
    0.46
    POSITIVE LOGITS
     aasta
    0.52
     आफ्टर
    0.52
    '(
    0.50
    bah
    0.50
    Beef
    0.49
    (
    0.49
    csrf
    0.49
    Hel
    0.48
    ちょっと
    0.48
    Biggest
    0.48
    Activations Density 0.001%

    No Known Activations