© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181224
    Prev
    Next
    INDEX
    Explanations

    PDO, SQL, JAVA, CXX, ALCHEMY, popen, pack

    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_24_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
    ੰਜ
    0.39
     pédicule
    0.39
     درسنا
    0.38
     герой
    0.38
    ύν
    0.36
     mécanique
    0.35
    離
    0.35
    ッズ
    0.35
    나라
    0.35
    ジナル
    0.34
    POSITIVE LOGITS
     Why
    0.41
    free
    0.40
    zug
    0.40
    ashing
    0.39
     plugins
    0.38
    additional
    0.38
     Lava
    0.37
     to
    0.37
     DO
    0.37
    ash
    0.37
    Activations Density 0.001%

    No Known Activations