© 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. 41-GEMMASCOPE-2-RES-262K
    7. 23362
    Prev
    Next
    INDEX
    Explanations

    masked autoencoder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     결과
    0.42
    לות
    0.42
    ុន
    0.41
    Fan
    0.41
     fan
    0.40
    צא
    0.40
    총
    0.39
     Comerc
    0.39
    逗
    0.39
     팬
    0.39
    POSITIVE LOGITS
     อายุ
    0.43
     imassa
    0.38
    ised
    0.38
    TRUE
    0.38
    SMTP
    0.37
    式
    0.37
    
    0.36
     patterned
    0.36
     vesicular
    0.36
     elle
    0.36
    Activations Density 0.001%

    No Known Activations