© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109463
    Prev
    Next
    INDEX
    Explanations

    stop-motion, stop-loss, f-stop

    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_1_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
    ל
    1.09
    א
    1.09
    ক
    1.04
    اً
    1.03
    á
    1.03
    "
    1.02
    ي
    1.02
    на
    0.97
    ,
    0.93
    POSITIVE LOGITS
    do
    0.93
    the
    0.89
    ting
    0.89
    an
    0.88
    με
    0.87
    dates
    0.87
    drinks
    0.86
    ten
    0.84
    dogs
    0.84
    un
    0.83
    Activations Density 0.001%

    No Known Activations