© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152664
    Prev
    Next
    INDEX
    Explanations

    sorting pivot

    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_23_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
     FRANCE
    0.47
     ITALY
    0.43
     führen
    0.42
    tableFuture
    0.41
     France
    0.41
     Itália
    0.40
    ম
    0.39
    ITECT
    0.39
    ಫ್
    0.39
     história
    0.38
    POSITIVE LOGITS
    三個
    0.43
    三个
    0.42
    長的
    0.39
     peng
    0.39
    GetString
    0.39
    cartoon
    0.38
     दोगु
    0.38
    棍
    0.38
     Async
    0.37
    watercolor
    0.37
    Activations Density 0.002%

    No Known Activations