© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198838
    Prev
    Next
    INDEX
    Explanations

    .

    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_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
     ಬಿಯ
    0.42
    বিড়
    0.40
    
    0.39
     আন্দোল
    0.39
     Barbara
    0.38
    उंड
    0.37
    叨
    0.37
    燿
    0.37
    Chloe
    0.37
     dole
    0.37
    POSITIVE LOGITS
     eas
    0.38
     tenders
    0.37
    եկ
    0.37
    erals
    0.36
     injective
    0.35
    ังสือ
    0.35
     SF
    0.35
    Pag
    0.34
     näher
    0.34
     tal
    0.34
    Activations Density 0.001%

    No Known Activations