© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216566
    Prev
    Next
    INDEX
    Explanations

    commas and lists

    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_31_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
     conducive
    0.39
    侪
    0.36
    ineda
    0.35
     Ced
    0.33
    śc
    0.33
     landed
    0.33
     verwendeten
    0.33
    ளுக்கான
    0.32
    
    0.32
    ोरेशन
    0.32
    POSITIVE LOGITS
    ،
    0.80
    ,
    0.70
    ，
    0.63
    ၊
    0.62
     ،
    0.61
    ፣
    0.57
     ,
    0.56
     ፣
    0.56
    、
    0.52
    ,\
    0.49
    Activations Density 0.003%

    No Known Activations