© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102750
    Prev
    Next
    INDEX
    Explanations

    proceeds of, from, to

    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_14_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
     سە
    0.55
    makes
    0.55
    кость
    0.54
     constitución
    0.53
    bors
    0.52
    ੋ
    0.52
    സ്റ്റി
    0.52
     やす
    0.51
     peculi
    0.50
     annoyed
    0.50
    POSITIVE LOGITS
    et
    0.59
     angeles
    0.55
    ข้อมูล
    0.53
     received
    0.53
    ellingen
    0.52
    m
    0.52
     Jn
    0.51
    atown
    0.51
     Information
    0.50
    德
    0.49
    Activations Density 0.000%

    No Known Activations