© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18775
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ded
    0.42
     Deb
    0.41
    ha
    0.40
    僳
    0.39
     dedic
    0.39
     Ded
    0.39
     lider
    0.39
    HA
    0.38
    дә
    0.37
    apay
    0.37
    POSITIVE LOGITS
    ជំ
    0.38
    実践
    0.37
    ogado
    0.36
     migliorare
    0.36
    純
    0.36
    ଼
    0.36
    形式
    0.35
    自動
    0.35
     سیاسی
    0.34
     রাজনৈতিক
    0.34
    Activations Density 0.000%

    No Known Activations