© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31800
    Prev
    Next
    INDEX
    Explanations

    model

    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_50_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
    佘
    0.40
    NS
    0.40
    N
    0.37
     N
    0.37
     adipis
    0.37
    ême
    0.36
    ěstí
    0.36
    Á
    0.36
    Nintendo
    0.36
    Nes
    0.36
    POSITIVE LOGITS
     మహా
    0.41
    oshin
    0.41
     BM
    0.39
     सॉल्यू
    0.38
     Eve
    0.38
     currentValue
    0.37
    出的
    0.36
     Barth
    0.36
     оре
    0.36
    
    0.36
    Activations Density 0.001%

    No Known Activations