© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20758
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     가게
    0.38
     sàng
    0.38
     ആരാ
    0.36
     tersangka
    0.35
     দোষ
    0.35
    seva
    0.34
    
    0.34
     InputAction
    0.34
     koci
    0.33
    ząd
    0.33
    POSITIVE LOGITS
    ↵↵
    0.59
    >,</
    0.38
    ,\"
    0.36
    ,”
    0.36
    $/,
    0.34
    ,"
    0.34
     потра
    0.34
    ,:
    0.33
    क्ष
    0.33
    тацию
    0.33
    Activations Density 0.829%

    No Known Activations