© 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. 86602
    Prev
    Next
    INDEX
    Explanations

    U.S. states, world, europe

    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
    劷
    0.42
     FORM
    0.39
     Renaissance
    0.38
     Stap
    0.38
     разрабо
    0.38
     Scala
    0.37
     世
    0.37
     CORE
    0.37
     PATH
    0.37
     OA
    0.37
    POSITIVE LOGITS
    szer
    0.44
     temporadas
    0.42
    전거
    0.39
     harbor
    0.37
    莒
    0.37
    Voy
    0.37
     जाहीर
    0.37
     harbors
    0.37
    igur
    0.36
    șit
    0.36
    Activations Density 0.002%

    No Known Activations