© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30808
    Prev
    Next
    INDEX
    Explanations

    VR visualization

    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_31_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
    运营
    0.46
     metastability
    0.41
    ভাষা
    0.39
    serviceTime
    0.39
    癃
    0.37
     координаты
    0.36
    Coordinator
    0.35
    嗆
    0.34
     गुस्सा
    0.34
     координа
    0.34
    POSITIVE LOGITS
     visualization
    0.61
     visualizing
    0.57
     visualisation
    0.56
     visualizations
    0.54
     visualized
    0.54
    visualization
    0.51
     visualize
    0.50
     Visualization
    0.49
     Visualize
    0.49
     visualise
    0.49
    Activations Density 0.108%

    No Known Activations