© 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. 53544
    Prev
    Next
    INDEX
    Explanations

    mathematical function/process/formula/object

    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
    gui
    0.39
    力的
    0.35
     어떻
    0.35
    čių
    0.35
    POSIX
    0.35
     seasonally
    0.35
    eonium
    0.34
    
    0.34
    graphics
    0.34
     पर्य
    0.34
    POSITIVE LOGITS
    廛
    0.38
     Fitzpatrick
    0.38
     viewport
    0.37
     contentView
    0.37
     Manning
    0.37
     inclusivity
    0.37
     Infirm
    0.37
     adım
    0.36
     Ferguson
    0.36
     Manufact
    0.36
    Activations Density 0.008%

    No Known Activations