© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83212
    Prev
    Next
    INDEX
    Explanations

    specific terms or concepts

    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_53_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
    তাবাদ
    0.39
     Sukh
    0.38
     contened
    0.37
     assemblage
    0.37
    Assembl
    0.36
    ጼ
    0.36
     আরা
    0.36
     chauff
    0.35
    loess
    0.35
    Sem
    0.34
    POSITIVE LOGITS
    ವರಿಗೆ
    0.38
    عل
    0.35
    彦
    0.35
     Decision
    0.35
     individuales
    0.35
     ಮಕ್ಕ
    0.35
    ்கள்
    0.34
     τό
    0.33
     மக்கள்
    0.33
     einzel
    0.33
    Activations Density 0.015%

    No Known Activations