© 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. 34106
    Prev
    Next
    INDEX
    Explanations

    baking powder

    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
    <0xBF>
    0.72
     don
    0.67
    <
    0.66
    <0xAB>
    0.59
    {
    0.59
    ור
    0.57
    та
    0.57
     συνεργ
    0.56
    <0x92>
    0.56
    可以用
    0.56
    POSITIVE LOGITS
    t
    1.13
    ot
    0.81
    d
    0.77
    人
    0.75
    ad
    0.73
    s
    0.73
     .
    0.70
    Icons
    0.68
    Azure
    0.68
    ت
    0.67
    Activations Density 0.001%

    No Known Activations