© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150234
    Prev
    Next
    INDEX
    Explanations

    building

    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_59_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
    en
    0.43
    ிறேன்
    0.38
    em
    0.38
     lintas
    0.38
     K
    0.38
     dajj
    0.37
     ក
    0.37
    㬰
    0.37
     К
    0.36
    n
    0.36
    POSITIVE LOGITS
     building
    0.71
     बिल्डिंग
    0.71
     Building
    0.70
    Building
    0.70
     BUILDING
    0.70
    building
    0.68
     বিল্ডিং
    0.57
     Bldg
    0.57
     bâtiment
    0.54
     budynku
    0.53
    Activations Density 0.003%

    No Known Activations