© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28490
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

    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
     God
    1.95
    God
    1.76
     god
    1.60
    god
    1.43
    神
    1.30
     GOD
    1.29
     الله
    1.26
     Бог
    1.23
    GOD
    1.20
     Gods
    1.16
    POSITIVE LOGITS
     geometria
    0.37
    的生活
    0.36
    ICPSR
    0.36
    尊
    0.35
    CONF
    0.34
    zach
    0.34
    BorderStyle
    0.33
    ীদ
    0.33
    addSql
    0.33
    IGI
    0.33
    Activations Density 0.056%

    No Known Activations