© 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. 12646
    Prev
    Next
    INDEX
    Explanations

    polynomial degree

    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
    icae
    0.36
    ೈನ
    0.36
    жит
    0.35
    𝔪
    0.33
     নিষ্পত্তি
    0.33
     преподава
    0.33
    𝕡
    0.33
    cH
    0.32
    ப்பு
    0.31
    
    0.31
    POSITIVE LOGITS
     degree
    2.42
     Degree
    2.31
    Degree
    2.27
    degree
    2.22
     degrees
    2.13
     Degrees
    1.96
    degrees
    1.86
     डिग्री
    1.79
    Degrees
    1.79
     degré
    1.73
    Activations Density 0.100%

    No Known Activations