© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5535
    Prev
    Next
    INDEX
    Explanations

    partial derivatives

    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
     Produkt
    0.40
     product
    0.38
    㹂
    0.38
    presentableId
    0.37
    rá
    0.36
    rade
    0.36
    lä
    0.36
    悳
    0.36
    product
    0.35
    ramos
    0.35
    POSITIVE LOGITS
    partial
    0.63
    ∂
    0.56
    Partial
    0.54
     ∂
    0.54
     partial
    0.52
    ∂</
    0.49
     Partial
    0.48
     parcial
    0.47
    /∂
    0.44
    hame
    0.44
    Activations Density 0.039%

    No Known Activations