© 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. 216556
    Prev
    Next
    INDEX
    Explanations

    capitalized letters

    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
    摯
    0.28
     ው
    0.27
    يف
    0.25
     knife
    0.25
    requestFocus
    0.24
    ির্ব
    0.24
     réun
    0.24
    عو
    0.24
    況
    0.24
    鸯
    0.24
    POSITIVE LOGITS
     রাজধানী
    0.28
     kapital
    0.27
     capitalized
    0.27
     passar
    0.26
    capital
    0.26
    ieties
    0.25
     Capitals
    0.25
     semasa
    0.25
     پروت
    0.25
    ”）
    0.25
    Activations Density 0.002%

    No Known Activations