© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226528
    Prev
    Next
    INDEX
    Explanations

    DSN assignments

    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_6_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
    0
    0.98
     لأ
    0.93
    Το
    0.92
    Мо
    0.89
     noirs
    0.89
    for
    0.88
    Ре
    0.87
    Від
    0.87
    Очень
    0.86
     iniz
    0.86
    POSITIVE LOGITS
    al
    1.09
     is
    1.05
    p
    1.02
    л
    1.02
    -
    0.95
    ل
    0.92
    да
    0.89
     sanit
    0.88
    า
    0.86
     on
    0.85
    Activations Density 0.000%

    No Known Activations