© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88156
    Prev
    Next
    INDEX
    Explanations

    preheat oven

    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
    0
    1.07
    -
    0.84
    ل
    0.72
    вих
    0.70
    т
    0.69
    ，
    0.69
    ors
    0.66
    ক্ষার
    0.65
    ，「
    0.65
    EY
    0.64
    POSITIVE LOGITS
    on
    0.88
    ти
    0.88
     on
    0.88
    ص
    0.78
    tor
    0.64
    cknowled
    0.62
    し
    0.62
    торой
    0.61
    人
    0.61
    说是
    0.59
    Activations Density 0.005%

    No Known Activations