© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173688
    Prev
    Next
    INDEX
    Explanations

    countdown timer or clock

    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_20_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
    安全
    0.49
    操作
    0.47
    芷
    0.45
    家
    0.44
    긁
    0.43
    꿔
    0.41
    攬
    0.40
    滚
    0.40
     accessory
    0.40
    Introducing
    0.40
    POSITIVE LOGITS
     Counselor
    0.41
     ಪಕ್ಷ
    0.40
     Barrett
    0.39
    HOR
    0.39
    バリー
    0.39
    specificity
    0.39
    穼
    0.38
    ioon
    0.38
     ಸಿ
    0.38
     えっ
    0.38
    Activations Density 0.001%

    No Known Activations