© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206464
    Prev
    Next
    INDEX
    Explanations

    power and USB connectors

    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
    ად
    0.45
    eran
    0.38
    respArray
    0.37
    纜
    0.36
    Kings
    0.36
    arnya
    0.35
    Ocean
    0.35
    鹏
    0.35
    মন্ত্রীর
    0.34
    瑛
    0.34
    POSITIVE LOGITS
     spin
    0.42
    uy
    0.40
     program
    0.39
     SV
    0.39
     PROGRAM
    0.39
     कार्यक्रम
    0.38
     FileMode
    0.38
     listening
    0.38
     franchise
    0.38
    cie
    0.38
    Activations Density 0.000%

    No Known Activations