© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135316
    Prev
    Next
    INDEX
    Explanations

    app followed by ) or led

    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_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     powied
    0.96
     که
    0.95
     μια
    0.94
     reshaping
    0.89
    </h3>
    0.86
    chanical
    0.84
    ınızı
    0.84
    \}.
    0.81
    \
    0.80
    ured
    0.80
    POSITIVE LOGITS
    de
    1.09
    على
    1.08
    з
    1.01
    ig
    1.00
    ست
    0.99
    ة
    0.99
    í
    0.96
    id
    0.96
    ка
    0.95
    lja
    0.95
    Activations Density 0.001%

    No Known Activations