© 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. 88626
    Prev
    Next
    INDEX
    Explanations

    materials, audience, population, academic

    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
     países
    0.54
    o
    0.54
    to
    0.54
    CJK
    0.52
    lica
    0.50
     berühm
    0.49
    date
    0.49
     anderen
    0.48
    周
    0.48
    ERK
    0.48
    POSITIVE LOGITS
    ות
    0.52
     safeguards
    0.49
    ותו
    0.48
     delaying
    0.48
     rejuven
    0.47
     elution
    0.46
    های
    0.46
     resonances
    0.46
     seizing
    0.46
     enveloping
    0.46
    Activations Density 0.000%

    No Known Activations