© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 790
    Prev
    Next
    INDEX
    Explanations

    assigning roles or items

    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_39_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
     give
    1.20
    Give
    1.20
     Give
    1.16
     giving
    1.14
    给予
    1.11
    give
    1.09
    給
    1.09
    给
    1.08
     GIVE
    1.03
    giving
    0.99
    POSITIVE LOGITS
     chores
    0.39
     উপেক্ষা
    0.38
     Combining
    0.38
    ით
    0.38
     delves
    0.38
     consideration
    0.37
     Consideration
    0.37
    न्छ
    0.37
     compito
    0.36
     respons
    0.36
    Activations Density 0.064%

    No Known Activations