© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142974
    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_46_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
    НУ
    0.38
    prüsü
    0.37
    밍
    0.36
     milestone
    0.36
    میر
    0.35
     partic
    0.35
    тру
    0.34
    ",[(
    0.34
    διο
    0.34
    メン
    0.34
    POSITIVE LOGITS
    ómica
    0.40
    儡
    0.38
    Storage
    0.38
    Peaks
    0.38
    odoro
    0.37
    ộp
    0.37
     घटा
    0.37
     greed
    0.37
    isle
    0.37
     корпора
    0.37
    Activations Density 0.000%

    No Known Activations