© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45194
    Prev
    Next
    INDEX
    Explanations

    shapes contain jewelry

    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_13_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
    임을
    0.51
    ابعة
    0.46
     extracción
    0.45
    물
    0.45
    вало
    0.44
    ფორ
    0.44
    wski
    0.44
    گزاری
    0.43
    월
    0.43
    물이
    0.43
    POSITIVE LOGITS
    na
    0.56
    ga
    0.55
    ana
    0.50
    .");
    0.50
    asi
    0.50
    на
    0.49
    ")
    0.48
    rod
    0.48
    ger
    0.47
     ger
    0.47
    Activations Density 0.000%

    No Known Activations