© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130730
    Prev
    Next
    INDEX
    Explanations

    right-to-left processingparsing digitsalgorithms

    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_25_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
     matchList
    0.44
    гей
    0.43
    逮
    0.39
    перыі
    0.38
    حر
    0.38
     फैक्टर
    0.37
    厌
    0.37
     Bagley
    0.37
     sue
    0.36
    ییر
    0.36
    POSITIVE LOGITS
    nonatomic
    0.43
    itabbo
    0.41
     nominally
    0.38
     nomenclature
    0.37
    廃棄
    0.37
     nocturnal
    0.36
     mirada
    0.36
     yattha
    0.36
     각
    0.36
     '/
    0.35
    Activations Density 0.000%

    No Known Activations