© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202038
    Prev
    Next
    INDEX
    Explanations

    confluence

    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_12_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
     сю
    0.55
     occ
    0.54
    ects
    0.52
     mund
    0.51
     extremities
    0.50
     choices
    0.50
     asympt
    0.49
     ε
    0.49
     livres
    0.48
     quarta
    0.48
    POSITIVE LOGITS
    emiz
    0.55
    ینہ
    0.52
    Nigerian
    0.52
    Line
    0.52
    LoginID
    0.50
    Wine
    0.50
     yada
    0.50
    ;;
    0.50
    まず
    0.50
     پ
    0.49
    Activations Density 0.009%

    No Known Activations