© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166280
    Prev
    Next
    INDEX
    Explanations

    discretization of differential equations

    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_31_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
    owied
    0.40
     &$
    0.40
     saltwater
    0.39
     তেলে
    0.39
     Steuer
    0.37
     திரும
    0.37
     стратеги
    0.37
     refs
    0.37
    employed
    0.37
    䥑
    0.36
    POSITIVE LOGITS
    hev
    0.44
     Waiver
    0.39
     Bloss
    0.39
     cristall
    0.39
     Cryst
    0.37
    ክ
    0.37
     cryst
    0.35
     Enter
    0.35
     crystal
    0.35
     Deport
    0.35
    Activations Density 0.039%

    No Known Activations