© 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. 162334
    Prev
    Next
    INDEX
    Explanations

    structured formal detailed explanations

    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
     Macon
    0.38
    ChildScrollView
    0.38
    upuncture
    0.37
     പരി
    0.37
    Aaron
    0.36
    
    0.35
    ต่อ
    0.35
    Hourly
    0.35
     Franz
    0.34
     Watanabe
    0.33
    POSITIVE LOGITS
     detailed
    0.45
     formal
    0.43
    formal
    0.39
    #'
    0.38
     RST
    0.38
    Formal
    0.38
    実際に
    0.38
     Detailed
    0.38
    โลก
    0.37
    正式
    0.36
    Activations Density 0.079%

    No Known Activations