© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108736
    Prev
    Next
    INDEX
    Explanations

    adoring / adoringly / adoration

    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_2_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
    یت
    1.17
    :
    0.95
     불구하고
    0.90
    <0x0D>
    0.89
     পরই
    0.89
    $?
    0.89
     дверь
    0.89
    3
    0.88
    apat
    0.86
     распростра
    0.84
    POSITIVE LOGITS
    p
    2.05
    ت
    1.95
    ด
    1.73
    т
    1.64
    el
    1.57
    ри
    1.55
    m
    1.55
    त
    1.54
    ي
    1.54
    س
    1.51
    Activations Density 0.000%

    No Known Activations