© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135414
    Prev
    Next
    INDEX
    Explanations

    utility followed by common nouns

    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
    Negative Logits
    ین
    1.16
    지
    1.11
    ア
    1.03
    も
    1.00
    ک
    0.97
    도
    0.93
    न
    0.90
     یا
    0.90
    to
    0.89
    الی
    0.89
    POSITIVE LOGITS
    <0xA1>
    1.09
    ä
    1.04
    ského
    1.01
    0.99
    ský
    0.98
    <0x8F>
    0.96
     überzeugt
    0.94
    ag
    0.92
    <0x8C>
    0.91
    <0x97>
    0.90
    Activations Density 0.001%

    No Known Activations