© 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. 136642
    Prev
    Next
    INDEX
    Explanations

    numpy arrays processing and modeling

    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
     Veranstaltungen
    0.40
     Hike
    0.39
    syntax
    0.39
     Oatmeal
    0.39
     Mang
    0.38
    亚
    0.38
     syntax
    0.38
     Syntax
    0.38
    वर्षी
    0.38
     Bundest
    0.37
    POSITIVE LOGITS
    нтип
    0.42
     çağ
    0.39
     CALL
    0.38
    }^{+\
    0.38
     سنی
    0.38
     muslim
    0.37
    clf
    0.37
     مسلم
    0.36
    呼
    0.36
    ↻
    0.36
    Activations Density 0.003%

    No Known Activations