© 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. 179916
    Prev
    Next
    INDEX
    Explanations

    Origins and cultures

    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
     кон
    0.41
     mala
    0.40
    mala
    0.40
    Shi
    0.39
     फे
    0.38
    惭
    0.38
    Ruby
    0.37
    RAR
    0.37
    POC
    0.37
     cont
    0.36
    POSITIVE LOGITS
     Ilmu
    0.42
     Bang
    0.40
     delta
    0.40
    delta
    0.39
     Kenny
    0.39
    منٹ
    0.38
     Delta
    0.38
     U
    0.37
     Steve
    0.37
     Dale
    0.37
    Activations Density 0.022%

    No Known Activations