© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29
    Prev
    Next
    INDEX
    Explanations

    sense of

    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_40_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
    】,
    0.38
    \},
    0.34
    ាក់
    0.33
    jna
    0.33
    डा
    0.33
    okar
    0.33
    
    0.33
     tripartite
    0.32
     humidity
    0.32
     trout
    0.32
    POSITIVE LOGITS
    英寸
    0.39
     பெண்களுக்கு
    0.38
     Ə
    0.38
    সঙ্গে
    0.35
     २०२२
    0.35
    pyrazin
    0.34
    ებელი
    0.34
    itôt
    0.34
    싹
    0.34
    逺
    0.33
    Activations Density 1.571%

    No Known Activations