© 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. 33529
    Prev
    Next
    INDEX
    Explanations

    `filename` or `PNG`

    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
    ibid
    0.39
    REM
    0.37
     complejidad
    0.37
     воспита
    0.36
    throat
    0.36
    azaki
    0.36
     অপে
    0.36
    ***********
    0.36
    
    0.36
    anyone
    0.35
    POSITIVE LOGITS
     AM
    0.38
     डबल
    0.37
     CTR
    0.36
     terminals
    0.36
     ATR
    0.36
     ACR
    0.35
     glimmer
    0.35
     acta
    0.35
     AMA
    0.35
     اليمن
    0.35
    Activations Density 0.019%

    No Known Activations