© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 165499
    Prev
    Next
    INDEX
    Explanations

    compiled vs interpreted code

    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_34_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
    년을
    0.41
     costs
    0.41
    前辈
    0.39
    送
    0.39
    实时
    0.38
    成本
    0.37
    瓄
    0.37
    劻
    0.37
     förs
    0.36
    문제
    0.36
    POSITIVE LOGITS
     vary
    0.38
     imperfect
    0.37
     mature
    0.37
     चंद
    0.36
     Spotlight
    0.36
     служба
    0.35
    bq
    0.35
     adopters
    0.35
    testng
    0.34
    fling
    0.34
    Activations Density 0.012%

    No Known Activations