© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135184
    Prev
    Next
    INDEX
    Explanations

    tener a los siguientes

    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_6_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
    ור
    1.16
    ו
    0.93
    at
    0.92
     arme
    0.87
     ordine
    0.78
     etre
    0.78
     avoir
    0.77
     ancienne
    0.76
    it
    0.75
     hérit
    0.75
    POSITIVE LOGITS
    (
    0.96
    {
    0.77
    もら
    0.75
    *
    0.73
    [
    0.72
    ५
    0.72
    *(
    0.71
    も
    0.70
    <
    0.68
    \
    0.66
    Activations Density 0.000%

    No Known Activations