© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 762
    Prev
    Next
    INDEX
    Explanations

    view followed by box or port

    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
    财务
    0.38
     lock
    0.37
    ikuwa
    0.36
    lafen
    0.36
    swick
    0.36
    軲
    0.35
    anzas
    0.35
    窅
    0.34
    izon
    0.34
    奸
    0.34
    POSITIVE LOGITS
     view
    0.66
     Viewing
    0.62
     viewing
    0.59
    Viewing
    0.59
     viewed
    0.59
    观
    0.54
     View
    0.54
    view
    0.53
     VIEW
    0.53
     views
    0.51
    Activations Density 0.004%

    No Known Activations