© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57905
    Prev
    Next
    INDEX
    Explanations

    who followed by a verb

    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_11_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
    र
    0.66
     μπορούν
    0.64
     FPGA
    0.62
     lobbying
    0.62
    रेशन
    0.61
     McQu
    0.61
     μπορεί
    0.60
    の問題
    0.59
     voltaje
    0.59
     enfrenta
    0.56
    POSITIVE LOGITS
    {
    0.68
    dont
    0.57
    type
    0.57
     {
    0.54
    ags
    0.54
    ptic
    0.54
    tape
    0.53
    estimated
    0.52
    vede
    0.52
    groom
    0.51
    Activations Density 0.000%

    No Known Activations