© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 197832
    Prev
    Next
    INDEX
    Explanations

    is a thing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     ओपी
    0.39
    ক্ষিপ্ত
    0.39
     handsome
    0.39
     Idam
    0.39
    handsome
    0.38
    ム
    0.38
    твра
    0.38
     Municip
    0.38
    ópez
    0.38
    Hor
    0.37
    POSITIVE LOGITS
    可谓
    0.38
    -(-
    0.37
    罗
    0.37
    的前提
    0.36
    羅
    0.36
    䄳
    0.36
    คล
    0.35
     체
    0.35
     nails
    0.35
    సాగ
    0.35
    Activations Density 0.001%

    No Known Activations