© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89652
    Prev
    Next
    INDEX
    Explanations

    world dominated, saturated, or overflowing

    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_18_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
     смотрите
    0.42
    かを
    0.37
    áját
    0.37
     incorporar
    0.36
    憩
    0.36
    ucle
    0.36
     দেখো
    0.36
     ছিল
    0.35
    鏨
    0.35
     смотреть
    0.35
    POSITIVE LOGITS
     जहरी
    0.39
    жному
    0.39
    不知道
    0.39
    idade
    0.37
     لیکن
    0.36
    往往
    0.36
     bn
    0.35
    ἴ
    0.35
    जेश
    0.35
    贫
    0.35
    Activations Density 0.004%

    No Known Activations