© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40720
    Prev
    Next
    INDEX
    Explanations

    special education

    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
    Negative Logits
    ’
    1.00
    (
    0.81
    ,
    0.78
    t
    0.76
    ed
    0.73
    ت
    0.70
    '
    0.69
    <
    0.69
     weave
    0.68
     special
    0.67
    POSITIVE LOGITS
    ری
    0.92
    سی
    0.78
    ینی
    0.76
    فی
    0.75
     are
    0.74
    ність
    0.74
    жность
    0.72
    اری
    0.70
    د
    0.70
    ہی
    0.69
    Activations Density 0.002%

    No Known Activations