© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77772
    Prev
    Next
    INDEX
    Explanations

    That's or That is

    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_31_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
    㥳
    0.35
    ন্ত্র
    0.34
     শুধ
    0.34
    ってい
    0.34
     countenance
    0.34
     geweest
    0.34
    बै
    0.34
    MoodAnalyser
    0.34
    describe
    0.33
     выну
    0.33
    POSITIVE LOGITS
    帅
    0.37
     सूट
    0.37
     moul
    0.37
     شبه
    0.35
    ico
    0.35
     cot
    0.35
    setAdapter
    0.35
    ames
    0.34
     --->
    0.34
     mitad
    0.34
    Activations Density 0.003%

    No Known Activations