© 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. 39860
    Prev
    Next
    INDEX
    Explanations

    componentDidMount or componentDidUpdate

    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
    Negative Logits
    드의
    0.74
    트를
    0.72
    ಣ
    0.70
    Տ
    0.68
    ついて
    0.66
    }
    0.64
     ziua
    0.63
    ິ
    0.63
    ಸ್‌
    0.62
    に応じて
    0.62
    POSITIVE LOGITS
    m
    1.05
    م
    0.92
     for
    0.86
    ból
    0.85
    س
    0.83
    ا
    0.83
    V
    0.82
    ם
    0.80
    W
    0.79
    ع
    0.79
    Activations Density 0.001%

    No Known Activations