© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208300
    Prev
    Next
    INDEX
    Explanations

    Ministry of Health

    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_20_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
     ಮಾಡಿ
    0.46
    媛
    0.45
    धाम
    0.45
     messageShow
    0.43
    चेता
    0.43
    迷
    0.43
     सुनी
    0.43
     nhiều
    0.42
     यूनिवर्सिटी
    0.41
     saver
    0.40
    POSITIVE LOGITS
    უ
    0.44
    thus
    0.42
    os
    0.41
    ера
    0.40
    ometries
    0.39
    ი
    0.39
    omenclature
    0.39
    im
    0.39
    wier
    0.38
    ok
    0.38
    Activations Density 0.000%

    No Known Activations