© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2192
    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_39_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
    恁
    0.29
    oitte
    0.29
    depression
    0.29
     मिर्च
    0.29
     улицы
    0.28
    ückt
    0.28
    麹
    0.28
    不正
    0.27
     ब्रेस्ट
    0.27
    蝉
    0.27
    POSITIVE LOGITS
     ATT
    0.32
     lans
    0.32
     antagon
    0.31
     codified
    0.30
     Instagram
    0.29
     hop
    0.29
     cod
    0.28
     exploration
    0.28
     Exploration
    0.28
    ––
    0.28
    Activations Density 0.095%

    No Known Activations