© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131633
    Prev
    Next
    INDEX
    Explanations

    streamlit app titles

    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_6_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
    ת
    1.38
     on
    1.15
    ین
    1.10
    ul
    1.09
    ت
    1.01
    고
    1.00
    त
    0.97
    ای
    0.94
     in
    0.91
    os
    0.88
    POSITIVE LOGITS
    ková
    0.86
     ؟
    0.86
    お願い
    0.82
    groupBox
    0.81
    jdbcType
    0.80
     महत्त्व
    0.77
    backgroundColor
    0.77
    ffi
    0.77
    kk
    0.77
    ции
    0.76
    Activations Density 0.001%

    No Known Activations