© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248249
    Prev
    Next
    INDEX
    Explanations

    Guy

    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_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parallèle
    0.38
    chend
    0.37
     paralelo
    0.37
    書館
    0.37
    并发
    0.36
    роки
    0.35
    ロ
    0.34
    чений
    0.34
    ('%
    0.33
    万円
    0.33
    POSITIVE LOGITS
     Finder
    0.45
     Bartlett
    0.42
     Fairmont
    0.40
     Tuk
    0.39
     Schwab
    0.39
     Fabulous
    0.39
    Kuch
    0.39
     Presse
    0.39
     Forsyth
    0.38
     fairies
    0.38
    Activations Density 0.000%

    No Known Activations