© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41512
    Prev
    Next
    INDEX
    Explanations

    generalized statements

    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_22_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
     procured
    0.23
     civiles
    0.22
    typeof
    0.22
     `
    0.22
     negara
    0.21
     devised
    0.21
    сцю
    0.21
     ordering
    0.21
     values
    0.20
     globally
    0.20
    POSITIVE LOGITS
     მიმო
    0.23
    illator
    0.22
    愘
    0.22
     बद
    0.22
     инструмент
    0.22
    consulta
    0.22
    机会
    0.22
     افز
    0.22
    hne
    0.22
    闿
    0.21
    Activations Density 0.019%

    No Known Activations