© 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. 194785
    Prev
    Next
    INDEX
    Explanations

    the

    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
    精心
    0.38
     Dubey
    0.38
    ABI
    0.38
    Significant
    0.37
    显著
    0.36
     Navarro
    0.36
     bertujuan
    0.36
    锅
    0.36
    VertexBuffer
    0.35
     виртуа
    0.35
    POSITIVE LOGITS
     stell
    0.38
     Gr
    0.38
    oxyd
    0.37
    䤚
    0.36
    ieurs
    0.36
    (((
    0.35
     buget
    0.35
    ු
    0.35
    oculars
    0.34
    บอล
    0.34
    Activations Density 0.001%

    No Known Activations