© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173424
    Prev
    Next
    INDEX
    Explanations

    component or class creation

    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_20_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
    garn
    0.42
     garn
    0.40
     garnet
    0.39
     Mor
    0.39
     fell
    0.38
     like
    0.37
    М
    0.37
     garrison
    0.37
     stř
    0.37
    िखर
    0.37
    POSITIVE LOGITS
     প্রাস
    0.39
    内心
    0.39
    内に
    0.37
     расстояние
    0.36
    ╡
    0.36
     расстоя
    0.35
    وهات
    0.35
    utin
    0.35
     திருப்பி
    0.35
     تنها
    0.34
    Activations Density 0.001%

    No Known Activations