© 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. 96444
    Prev
    Next
    INDEX
    Explanations

    code formatting and delimiters

    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
    EN
    0.52
    ET
    0.50
    致命
    0.49
     campaign
    0.48
     Commission
    0.48
     =
    0.46
     Campaign
    0.46
     relativi
    0.45
    CreationFailed
    0.45
    Commission
    0.45
    POSITIVE LOGITS
    री
    0.55
    urada
    0.55
    »,
    0.54
    lendir
    0.53
    ())).
    0.52
     солнце
    0.51
    ancen
    0.51
    ते
    0.51
     peel
    0.50
    \},
    0.50
    Activations Density 0.011%

    No Known Activations