© 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. 173173
    Prev
    Next
    INDEX
    Explanations

    show commands and ui elements

    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
     Nhưng
    0.46
    %)
    0.44
     dishonest
    0.43
     Beyonce
    0.43
     Hanya
    0.42
    ടതി
    0.41
    ជាមួយ
    0.40
    ជាមួយនឹង
    0.40
     ஆனால்
    0.40
     malnourished
    0.40
    POSITIVE LOGITS
    :
    0.42
     없다
    0.39
    ä
    0.38
    tson
    0.36
    Det
    0.36
     vốn
    0.36
    
    0.36
    列
    0.36
    jeno
    0.35
    
    0.35
    Activations Density 0.000%

    No Known Activations