© 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. 136052
    Prev
    Next
    INDEX
    Explanations

    magnetic symmetry Bilbao Crystallographic Server

    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
    Dinner
    0.50
    com
    0.46
    col
    0.46
    dinner
    0.45
    ₸
    0.45
    t
    0.44
    B
    0.44
    Fot
    0.44
    Dining
    0.44
    णात
    0.44
    POSITIVE LOGITS
     divulg
    0.51
     elucidation
    0.51
     оде
    0.50
     מצ
    0.45
    繹
    0.45
     aggrieved
    0.44
     analyzed
    0.43
     acquitted
    0.43
     uj
    0.43
    硋
    0.42
    Activations Density 0.000%

    No Known Activations