© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78728
    Prev
    Next
    INDEX
    Explanations

    instructions or commands

    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_53_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
    ۔۔
    0.38
     ಅರ್ಜಿ
    0.36
    。</
    0.34
    ஸ்வர
    0.33
    ುತ್ತಿದ್ದ
    0.32
     मीरा
    0.31
     merkle
    0.31
     डाउट
    0.30
     `=`,
    0.30
     meninggal
    0.30
    POSITIVE LOGITS
     celé
    0.39
    或者是
    0.39
     é
    0.38
    出来ます
    0.38
    個
    0.37
     aforesaid
    0.37
    或是
    0.36
     somebody
    0.36
     või
    0.36
     अथवा
    0.35
    Activations Density 1.213%

    No Known Activations