© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 133633
    Prev
    Next
    INDEX
    Explanations

    card dealing

    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_37_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
     أج
    0.38
    든지
    0.38
    Integrated
    0.38
     tasa
    0.37
    ىن
    0.36
    粒
    0.36
    Embed
    0.36
     cb
    0.35
    ἱ
    0.35
    ୟ
    0.35
    POSITIVE LOGITS
     deal
    0.65
     Deal
    0.65
     deals
    0.61
     dealt
    0.61
    deal
    0.59
     dealing
    0.59
     DEAL
    0.57
    Deal
    0.56
     Deals
    0.55
     shuffling
    0.55
    Activations Density 0.002%

    No Known Activations