© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33463
    Prev
    Next
    INDEX
    Explanations

    code, programming, and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    x
    0.40
    )}$
    0.37
     Алек
    0.37
    blo
    0.36
    Islam
    0.35
    Marin
    0.35
     \%$
    0.35
    icina
    0.35
    ]}$
    0.35
    xx
    0.34
    POSITIVE LOGITS
     trading
    0.39
     भा
    0.38
     Spectral
    0.37
    やかに
    0.36
    ೇಯ
    0.36
    νά
    0.36
     cuadr
    0.35
     অ্যান্ড্র
    0.35
     monospace
    0.35
     рассматривать
    0.35
    Activations Density 0.045%

    No Known Activations