© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40881
    Prev
    Next
    INDEX
    Explanations

    term of agreement

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    них
    0.67
    ลูก
    0.58
    กัน
    0.57
    icks
    0.55
     "{
    0.55
    .
    0.55
     are
    0.54
    ";
    0.53
    ję
    0.53
    록
    0.53
    POSITIVE LOGITS
    f
    0.77
    Term
    0.73
    term
    0.71
    b
    0.66
    cerr
    0.66
    t
    0.64
    Successfully
    0.60
    ن
    0.59
    edited
    0.59
    ק
    0.58
    Activations Density 0.027%

    No Known Activations