© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6742
    Prev
    Next
    INDEX
    Explanations

    compile

    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_39_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
    Script
    0.38
     Gern
    0.37
    alary
    0.37
    嘌
    0.36
    ностями
    0.35
    instell
    0.35
    クトル
    0.35
     Joaquín
    0.35
    擱
    0.35
    舝
    0.35
    POSITIVE LOGITS
     compile
    2.28
     compilation
    2.14
     compiling
    2.06
     Compile
    2.06
     compiles
    2.05
    编译
    2.02
     Compilation
    1.99
    compile
    1.98
     compiled
    1.97
     compil
    1.92
    Activations Density 0.365%

    No Known Activations