© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88488
    Prev
    Next
    INDEX
    Explanations

    protective covering/shell

    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_18_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
     felis
    0.40
     Хабаров
    0.39
     hés
    0.38
    ण्यास
    0.38
     जेव्हा
    0.38
    电器
    0.38
     தீ
    0.37
    鲲
    0.36
    美食
    0.36
     احتجاج
    0.36
    POSITIVE LOGITS
    ale
    0.42
    analytical
    0.40
    ield
    0.40
    atlar
    0.39
     created
    0.39
     analytical
    0.38
    ofile
    0.38
    cedures
    0.38
    ouch
    0.38
    صدر
    0.38
    Activations Density 0.004%

    No Known Activations