© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87001
    Prev
    Next
    INDEX
    Explanations

    describe instance properties

    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_3_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
    导致的
    0.63
    昷
    0.62
    𝙣
    0.61
     договора
    0.60
    تون
    0.59
     refugi
    0.57
     жидкости
    0.57
     harán
    0.57
    半径
    0.57
    تك
    0.56
    POSITIVE LOGITS
     description
    0.88
    ם
    0.82
    Description
    0.82
     describe
    0.82
     desc
    0.80
    DESCRIPTION
    0.80
    ו
    0.79
     descriptions
    0.79
     Description
    0.78
     DESCRIPTION
    0.77
    Activations Density 0.003%

    No Known Activations