© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43887
    Prev
    Next
    INDEX
    Explanations

    papyrus scrolls, boats, papillomavirus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
     quitar
    0.76
    i
    0.75
     contrived
    0.72
     identificar
    0.70
     revolutionized
    0.70
    ộn
    0.68
     beneficio
    0.66
     diminuer
    0.66
     agregar
    0.65
    ي
    0.65
    POSITIVE LOGITS
    م
    0.80
    h
    0.72
    דות
    0.66
    א
    0.66
    ባድ
    0.65
     పాటు
    0.65
    K
    0.65
    os
    0.64
    用户
    0.63
    ని
    0.62
    Activations Density 0.001%

    No Known Activations