© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161428
    Prev
    Next
    INDEX
    Explanations

    age and demographics

    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_31_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
     आफ्टर
    0.30
    复制代码
    0.30
    予測
    0.29
    意外
    0.29
     Maa
    0.29
    [])
    0.29
    resistance
    0.28
     überras
    0.28
     biker
    0.28
    ্বার
    0.28
    POSITIVE LOGITS
     Liet
    0.36
    Chest
    0.36
     simpat
    0.33
     commandBuffer
    0.33
    canal
    0.32
    ၽ
    0.32
    十大
    0.32
    ulfide
    0.31
    馏
    0.31
     dine
    0.31
    Activations Density 0.002%

    No Known Activations