© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116395
    Prev
    Next
    INDEX
    Explanations

    capital of France

    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_27_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
    漂
    0.39
    ExprNode
    0.35
     planets
    0.35
     Fail
    0.35
     انسانی
    0.35
    噌
    0.35
     Figur
    0.35
     princes
    0.34
     Fill
    0.34
    Learn
    0.34
    POSITIVE LOGITS
    ("-"
    0.38
    榞
    0.38
     télévision
    0.38
     प्रेरणात्मक
    0.37
    international
    0.37
    export
    0.36
     motiva
    0.36
     tearing
    0.35
     expatri
    0.35
     играет
    0.35
    Activations Density 0.007%

    No Known Activations