© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32911
    Prev
    Next
    INDEX
    Explanations

    derivatives dy/dx, dr/dθ

    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
    𐰆
    0.39
     அன்ன
    0.38
    天上
    0.37
     ఉండ
    0.37
    ݢ
    0.37
    상품
    0.35
    Para
    0.35
     médiocrement
    0.34
    ᒧ
    0.34
     ਨਹੀਂ
    0.34
    POSITIVE LOGITS
     Cab
    0.42
     Cabo
    0.38
     Tad
    0.37
     প্রেক্ষিতে
    0.37
     cab
    0.36
     Good
    0.36
     Information
    0.36
     Criteria
    0.36
     CBA
    0.36
     Cabe
    0.36
    Activations Density 0.005%

    No Known Activations