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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197977
    Prev
    Next
    INDEX
    Explanations

    Russian statehood

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    랜드
    0.39
     caule
    0.39
    Ⲱ
    0.38
    뵈
    0.38
    埴
    0.38
    日程
    0.37
     обществе
    0.37
    ඒ
    0.37
    তীশ
    0.36
     пола
    0.36
    POSITIVE LOGITS
     Gos
    1.20
    Gos
    1.16
     gos
    1.13
    Го
    1.07
     го
    1.06
    gos
    1.05
     Го
    1.04
     гос
    0.93
    ゴ
    0.84
    го
    0.84
    Activations Density 0.000%

    No Known Activations