© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8728
    Prev
    Next
    INDEX
    Explanations

    left followed by ventricle, atrium, or lobe

    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_13_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
    com
    0.42
    ເນ
    0.37
    ra
    0.37
    रा
    0.35
    बीसी
    0.35
    ्रा
    0.34
    t
    0.34
    信息
    0.34
     لما
    0.34
    listing
    0.34
    POSITIVE LOGITS
    *)
    0.39
    )=
    0.38
     Democratic
    0.37
     carbonate
    0.37
    );
    0.35
    DUN
    0.35
     coronary
    0.34
     živ
    0.34
    )
    0.34
    🥤
    0.34
    Activations Density 0.038%

    No Known Activations