© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6887
    Prev
    Next
    INDEX
    Explanations

    JSON

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     자동으로
    0.41
     hàng
    0.40
     Vi
    0.40
     nau
    0.39
    Ⅵ
    0.38
    Vi
    0.38
     कॉम
    0.38
    Scar
    0.37
     ২১
    0.36
    bindo
    0.36
    POSITIVE LOGITS
    試合
    0.41
     chorizo
    0.41
    osť
    0.39
    㳚
    0.39
     crying
    0.38
     ERISA
    0.38
    orage
    0.37
     oxalate
    0.37
    チャ
    0.36
    メ
    0.36
    Activations Density 0.004%

    No Known Activations