© 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. 18664
    Prev
    Next
    INDEX
    Explanations

    order and family names

    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
    参加
    0.41
    간다
    0.40
     आदेश
    0.39
    參加
    0.37
     unenforceable
    0.36
    ளே
    0.35
     භ
    0.35
     яку
    0.35
     पत्रों
    0.35
    短暂
    0.35
    POSITIVE LOGITS
    蝸
    0.43
    core
    0.39
     togel
    0.38
     Suga
    0.37
    tos
    0.37
     Pharaoh
    0.37
     Tomcat
    0.37
    ']]
    0.36
     heartburn
    0.36
     stung
    0.36
    Activations Density 0.011%

    No Known Activations