© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18594
    Prev
    Next
    INDEX
    Explanations

    new exception argument

    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
     failure
    0.50
    failure
    0.47
    Failure
    0.47
     failures
    0.44
     FAILURE
    0.44
     Failure
    0.44
    ᚕ
    0.39
    失败
    0.38
     Слу
    0.38
     नाइट
    0.37
    POSITIVE LOGITS
     Combustion
    0.41
     metabolismo
    0.38
     pemer
    0.38
    System
    0.38
     Evel
    0.38
     divide
    0.37
    зин
    0.37
     Rockets
    0.37
     preoccup
    0.37
    RowFilter
    0.37
    Activations Density 0.002%

    No Known Activations