© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167759
    Prev
    Next
    INDEX
    Explanations

    meeting gaze

    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_34_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
     reunion
    0.42
     réunion
    0.41
     Uml
    0.38
    的人物
    0.37
     Clause
    0.37
     Lectures
    0.36
     recepción
    0.36
    <unused63>
    0.36
    ânica
    0.36
    Recipes
    0.36
    POSITIVE LOGITS
     سج
    0.41
     signalé
    0.38
     tern
    0.37
    mets
    0.37
    eda
    0.36
     قوه
    0.36
     util
    0.36
     exited
    0.36
     investigated
    0.35
     sock
    0.35
    Activations Density 0.003%

    No Known Activations