© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 206111
    Prev
    Next
    INDEX
    Explanations

    earth, stone, commodities

    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_25_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
     noticias
    0.27
     nCenters
    0.26
     notícias
    0.26
    랠
    0.26
    individu
    0.25
     点击
    0.25
     ので
    0.24
    zogen
    0.24
     llrp
    0.23
    下載
    0.23
    POSITIVE LOGITS
     E
    0.26
     Even
    0.23
     Eight
    0.23
     All
    0.22
     For
    0.22
     Terra
    0.22
     Nowadays
    0.21
     B
    0.21
     What
    0.21
     Stone
    0.21
    Activations Density 0.002%

    No Known Activations