© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16245
    Prev
    Next
    INDEX
    Explanations

    House, Senate, Roger Sherman, July, ratification

    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_40_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
    ઠ
    0.40
    бли
    0.37
    üsü
    0.36
    obie
    0.36
    طلب
    0.35
    Enabled
    0.35
     எம்
    0.35
    Oro
    0.34
     Enabled
    0.34
    statusBar
    0.34
    POSITIVE LOGITS
     Manager
    0.45
     Managers
    0.45
     Debate
    0.43
    aic
    0.40
    鿌
    0.40
     বিত
    0.39
     managers
    0.39
    manager
    0.38
     सप्त
    0.38
     Repert
    0.38
    Activations Density 0.012%

    No Known Activations