© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124189
    Prev
    Next
    INDEX
    Explanations

    90%

    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_37_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
    کم
    0.44
     अच्छे
    0.38
    Whe
    0.38
    ked
    0.36
    Dependency
    0.36
    Edd
    0.35
     первую
    0.35
    比
    0.35
     taxation
    0.34
    ipitation
    0.34
    POSITIVE LOGITS
    キロ
    0.38
     جنيه
    0.37
    "."
    0.37
    baj
    0.36
     सदस्यीय
    0.36
    分數
    0.36
    ညာ
    0.36
     showcasing
    0.36
    繃
    0.36
     metri
    0.35
    Activations Density 0.003%

    No Known Activations