© 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. 37144
    Prev
    Next
    INDEX
    Explanations

    good/approval

    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
     coy
    0.42
    定了
    0.41
     Jerzy
    0.39
     Gewerks
    0.39
    িমা
    0.38
     poorer
    0.38
     handicrafts
    0.38
    }}+
    0.37
     sech
    0.37
    odesmium
    0.36
    POSITIVE LOGITS
     bon
    0.64
    bon
    0.59
    Bon
    0.56
     Bon
    0.55
     bel
    0.54
     попа
    0.53
     belie
    0.50
    Bel
    0.50
    uman
    0.49
     Bel
    0.48
    Activations Density 0.003%

    No Known Activations