© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102876
    Prev
    Next
    INDEX
    Explanations

    behaving in a certain way

    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_1_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
    i
    1.17
    a
    0.98
    ი
    0.88
     quienes
    0.88
    ্সে
    0.88
    n
    0.87
    ޟ
    0.87
    dropped
    0.86
    ༠
    0.85
    an
    0.84
    POSITIVE LOGITS
    我
    1.32
    し
    1.29
    お
    1.24
    1
    1.22
    一
    1.20
    大
    1.17
    在
    1.12
    した
    1.10
    って
    1.10
    وم
    1.08
    Activations Density 0.001%

    No Known Activations