© 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. 135350
    Prev
    Next
    INDEX
    Explanations

    scikit-learn

    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
    ↵
    0.95
     في
    0.94
    gewicht
    0.88
    uer
    0.87
    oft
    0.86
    aff
    0.86
    Semester
    0.83
    ،
    0.83
    '،
    0.83
    apeut
    0.82
    POSITIVE LOGITS
     on
    1.24
    т
    1.05
     to
    1.04
     or
    1.02
    ל
    0.96
    ığı
    0.96
    த
    0.95
    써
    0.94
    ل
    0.94
    า
    0.89
    Activations Density 0.001%

    No Known Activations