© 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. 85425
    Prev
    Next
    INDEX
    Explanations

    language selection, attributes

    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
     I
    0.97
    -
    0.85
    \
    0.84
     It
    0.77
    <0x80>
    0.75
    <0xA8>
    0.74
    í
    0.72
    ır
    0.70
    ía
    0.69
    (
    0.67
    POSITIVE LOGITS
    ک
    1.00
    ウ
    0.80
    졌
    0.80
    پ
    0.79
    τη
    0.79
    k
    0.78
    لی
    0.78
    significant
    0.77
    ት
    0.77
    konto
    0.77
    Activations Density 0.000%

    No Known Activations