© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197858
    Prev
    Next
    INDEX
    Explanations

    employees and size

    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_12_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
     නිෂ්පා
    0.64
     свет
    0.62
    ❣️
    0.61
    omponent
    0.61
     العلام
    0.59
    ပါသည်။
    0.59
     ద
    0.59
     ಕ
    0.58
     عزی
    0.57
     рӯ
    0.57
    POSITIVE LOGITS
    $\
    0.61
    le
    0.59
    or
    0.58
    ino
    0.57
    \)
    0.56
    );
    0.55
    EM
    0.55
    </
    0.54
    \
    0.54
     management
    0.53
    Activations Density 0.005%

    No Known Activations