© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 134446
    Prev
    Next
    INDEX
    Explanations

    technical names

    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_50_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
     whenever
    0.42
     muni
    0.40
    む
    0.38
    崁
    0.38
    munk
    0.37
     End
    0.37
     Mukesh
    0.36
     Whenever
    0.36
     fasci
    0.36
     ti
    0.35
    POSITIVE LOGITS
    Cable
    0.41
    Convergence
    0.38
     Gine
    0.38
    etry
    0.37
    AX
    0.36
    odymium
    0.36
    卿
    0.36
    Graphical
    0.36
     Poetry
    0.36
    convergence
    0.35
    Activations Density 0.002%

    No Known Activations