© 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
    2. Gemma-3-27B-IT
    3. 6-GEMMASCOPE-2-TRANSCODER-262K
    4. 226842
    Prev
    Next
    INDEX
    Explanations

    you to

    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
    {
    0.95
    <0x80>
    0.87
    <0x99>
    0.82
     في
    0.76
    <0x8F>
    0.72
    {:
    0.72
    <0xA7>
    0.71
    et
    0.71
     in
    0.68
    вел
    0.68
    POSITIVE LOGITS
     to
    1.06
     that
    1.04
     and
    1.03
    ب
    0.93
     but
    0.89
    น
    0.88
    ज
    0.87
     ancien
    0.84
     ancienne
    0.84
     with
    0.83
    Activations Density 0.001%

    No Known Activations