© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85267
    Prev
    Next
    INDEX
    Explanations

    original request

    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_18_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
    Methoxy
    0.57
    Colorful
    0.52
    Laboratory
    0.51
    لی
    0.51
    ≈
    0.50
    Ethoxy
    0.50
    Lantern
    0.49
    CHARACTER
    0.48
    Terrain
    0.48
    PO
    0.48
    POSITIVE LOGITS
    ناع
    0.48
     changes
    0.46
    rante
    0.45
     conceived
    0.44
     }}$.
    0.44
     headings
    0.44
     Initiatives
    0.44
     Ensures
    0.44
    <0x98>
    0.43
    queryString
    0.43
    Activations Density 0.002%

    No Known Activations