© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93555
    Prev
    Next
    INDEX
    Explanations

    programming frameworks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     [
    0.45
    0.43
    "
    0.42
    ,"
    0.42
     '
    0.40
    ."
    0.40
    ?"
    0.40
    ".
    0.40
      
    0.38
     ~
    0.38
    POSITIVE LOGITS
    localVar
    0.46
    heatmap
    0.45
    gameState
    0.44
    axiom
    0.44
    xgb
    0.43
    parallax
    0.43
     Guarant
    0.43
    gazebo
    0.43
    intArray
    0.43
    groupBy
    0.42
    Activations Density 0.003%

    No Known Activations