© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33725
    Prev
    Next
    INDEX
    Explanations

    moving average cross period

    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_31_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
    frameNStart
    0.44
    鄴
    0.43
    臼
    0.40
    ATTLE
    0.39
     PAINE
    0.38
     republican
    0.38
    信息公示
    0.37
    getStudentNo
    0.37
    ⌯
    0.37
    \{-\
    0.36
    POSITIVE LOGITS
     waking
    0.41
     eğ
    0.38
    agents
    0.38
     ont
    0.38
     beige
    0.38
     age
    0.38
    兆
    0.38
     tiring
    0.37
     tendance
    0.36
     Commencez
    0.36
    Activations Density 0.067%

    No Known Activations