© 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. 27336
    Prev
    Next
    INDEX
    Explanations

    CREATE DATABASE LINK statement

    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
     knotted
    0.39
     DIFFIC
    0.39
     পারস্প
    0.38
    opus
    0.37
    ন্না
    0.37
    凝
    0.36
     amts
    0.35
     Perce
    0.35
    guard
    0.35
    Wax
    0.35
    POSITIVE LOGITS
    ⸝
    0.38
     segregation
    0.37
    噸
    0.37
    लों
    0.37
    <unused23>
    0.36
    ázquez
    0.36
     undocumented
    0.36
     dirt
    0.35
    ઓની
    0.35
     satunya
    0.35
    Activations Density 0.018%

    No Known Activations