© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19760
    Prev
    Next
    INDEX
    Explanations

    compound word formation

    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_15_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
     الكسور
    0.54
    牖
    0.53
     spok
    0.52
    рованием
    0.52
    ровала
    0.50
    Khokhlov
    0.49
     convolutions
    0.49
    簋
    0.48
    萦
    0.48
     بالله
    0.48
    POSITIVE LOGITS
    </h2>
    0.52
    cald
    0.51
    ’,
    0.50
    tea
    0.50
    mil
    0.49
    es
    0.47
    nis
    0.47
    iguation
    0.47
    ży
    0.46
    JMenuItem
    0.46
    Activations Density 0.002%

    No Known Activations