© 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. 75377
    Prev
    Next
    INDEX
    Explanations

    MIT License

    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
     couverture
    0.47
     جوس
    0.41
     अधिकारी
    0.41
    isinde
    0.40
    𝕣
    0.39
    minic
    0.38
    нік
    0.38
    roweak
    0.37
    嫘
    0.37
    روف
    0.37
    POSITIVE LOGITS
    गार
    0.42
    llllllll
    0.39
     போட்டிய
    0.38
     hall
    0.38
    左
    0.36
     gratis
    0.36
     viên
    0.36
    HALL
    0.36
    γων
    0.35
    斯科
    0.35
    Activations Density 0.000%

    No Known Activations