© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75653
    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_31_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
    ★★
    0.35
    theorem
    0.35
    鹸
    0.35
    CND
    0.34
     Бар
    0.34
     Defensive
    0.34
     рр
    0.34
     Θε
    0.34
    Theorem
    0.33
    forKey
    0.33
    POSITIVE LOGITS
     powerless
    0.40
     управлять
    0.39
     смогли
    0.39
     ಬೇಕ
    0.38
     fellow
    0.38
    由
    0.38
     rely
    0.37
     Rely
    0.37
     converged
    0.36
     ಜಿಲ್ಲ
    0.36
    Activations Density 0.000%

    No Known Activations