© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34247
    Prev
    Next
    INDEX
    Explanations

    Wo

    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_50_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
    мец
    0.42
     próp
    0.41
    lake
    0.40
    quinoxaline
    0.40
     こう
    0.38
    ່າຍ
    0.37
    ሐ
    0.36
     দ্রব
    0.36
    isAuthenticated
    0.36
    एप
    0.35
    POSITIVE LOGITS
    Wo
    1.18
     Wo
    1.17
     wo
    1.16
     WO
    1.12
    wo
    0.99
    WO
    0.93
     W
    0.82
     Woh
    0.82
     Woj
    0.78
    Woh
    0.77
    Activations Density 0.044%

    No Known Activations