© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238518
    Prev
    Next
    INDEX
    Explanations

    is

    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
    日常生活
    0.28
    정에
    0.27
     lb
    0.27
    做出
    0.27
     হালকা
    0.26
    饼
    0.26
    主要是
    0.25
     кантип
    0.25
    esseur
    0.25
    Bour
    0.25
    POSITIVE LOGITS
    らっしゃ
    0.29
     repress
    0.28
     फलस्वरूप
    0.28
     populous
    0.27
    ṭ
    0.27
     accomplishment
    0.27
     explica
    0.26
     energie
    0.26
     China
    0.26
     ecology
    0.26
    Activations Density 0.012%

    No Known Activations