© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41356
    Prev
    Next
    INDEX
    Explanations

    as ... format

    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_11_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
    k
    0.74
     Taxonomy
    0.61
    a
    0.61
    ا
    0.60
     Información
    0.57
    nere
    0.57
     Inference
    0.57
    kün
    0.56
    produk
    0.56
    ि
    0.55
    POSITIVE LOGITS
     כי
    0.59
     chast
    0.57
     vies
    0.56
    ור
    0.55
     key
    0.54
     την
    0.54
     בת
    0.52
     sa
    0.52
     maar
    0.52
     sun
    0.50
    Activations Density 0.039%

    No Known Activations