© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 247921
    Prev
    Next
    INDEX
    Explanations

    must

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    COMING
    0.41
     Input
    0.39
    Backed
    0.38
    랬
    0.38
    ம்மா
    0.38
    Notifications
    0.38
     রানী
    0.38
     Notifications
    0.38
    фера
    0.37
    Input
    0.36
    POSITIVE LOGITS
     lay
    0.49
     meet
    0.46
    Meet
    0.44
     Lay
    0.42
     Meet
    0.42
    Lay
    0.42
    s
    0.41
     objed
    0.41
    meet
    0.41
     LAY
    0.41
    Activations Density 0.003%

    No Known Activations