© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171077
    Prev
    Next
    INDEX
    Explanations

    past performance is not indicative of future results

    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_20_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
     그러면은
    0.22
     ehemalige
    0.22
     निर्धारित
    0.21
     course
    0.21
     प्रतिकूल
    0.21
    骧
    0.20
    course
    0.19
     খ্র
    0.19
    եկ
    0.19
     کررہے
    0.19
    POSITIVE LOGITS
    홉
    0.23
     꿈
    0.21
     bumpers
    0.21
     posibilidades
    0.21
    ໂດ
    0.21
     volupt
    0.20
    🠀
    0.20
    錦
    0.20
     forman
    0.20
     mog
    0.20
    Activations Density 0.001%

    No Known Activations