© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200313
    Prev
    Next
    INDEX
    Explanations

    set

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     السماء
    0.37
    ವೆ
    0.36
    妻子
    0.35
    brushes
    0.34
    ंजी
    0.33
    EARCH
    0.33
    @(
    0.33
    _{[
    0.32
    heses
    0.32
    toprule
    0.32
    POSITIVE LOGITS
     set
    2.13
     sets
    2.00
    セット
    1.88
     सेट
    1.82
     Sets
    1.80
     набор
    1.80
     Set
    1.77
     সেট
    1.73
    set
    1.67
    Set
    1.66
    Activations Density 0.139%

    No Known Activations