© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9424
    Prev
    Next
    INDEX
    Explanations

    exam conduct

    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
     passed
    0.52
     passing
    0.51
     pass
    0.49
    passing
    0.48
    passed
    0.45
    Passed
    0.45
     Passing
    0.44
    渡
    0.44
     Passed
    0.44
    pass
    0.41
    POSITIVE LOGITS
    conduct
    0.59
    Conduct
    0.57
     conduct
    0.57
     Conduct
    0.57
    Computer
    0.53
     conducts
    0.52
     conducting
    0.51
    CONDUCT
    0.50
     CONDUCT
    0.49
     Conducting
    0.49
    Activations Density 0.006%

    No Known Activations