© 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. 206872
    Prev
    Next
    INDEX
    Explanations

    from/by

    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
    '
    1.47
    <0x80>
    1.23
    á
    1.20
    ut
    1.16
    ш
    1.13
    и
    1.09
    ah
    1.08
    то
    1.07
    um
    1.06
    "
    1.05
    POSITIVE LOGITS
     by
    1.03
     जियोग्राफी
    1.02
    াহিয়া
    0.93
     an
    0.93
    াহিয়ার
    0.86
     النظام
    0.85
     automorphism
    0.83
     Aufnahme
    0.83
     История
    0.83
    nommen
    0.82
    Activations Density 0.000%

    No Known Activations