© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200709
    Prev
    Next
    INDEX
    Explanations

    Napoleon's campaigns and defeats

    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
     national
    0.52
    ាល
    0.50
     CO
    0.50
    BL
    0.49
     Napoleon
    0.49
     west
    0.49
     Ministry
    0.48
     l
    0.48
    uro
    0.48
    gist
    0.48
    POSITIVE LOGITS
    meler
    0.56
    JsonKey
    0.55
     económ
    0.54
     பொது
    0.52
    卄
    0.52
     договор
    0.50
     acuer
    0.50
     insuff
    0.49
     bermain
    0.49
     Jahren
    0.49
    Activations Density 0.001%

    No Known Activations