© 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. 136785
    Prev
    Next
    INDEX
    Explanations

    aria attributes

    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
    /<
    0.36
    aund
    0.35
    Ple
    0.35
     EXPECT
    0.35
     comentar
    0.34
    prü
    0.34
    Читать
    0.34
    Э
    0.34
    ENABLE
    0.34
     cans
    0.33
    POSITIVE LOGITS
     fermentum
    0.41
    ുകയാണ്
    0.39
     blushed
    0.38
     कुशवाहा
    0.38
     Mitar
    0.36
    writelines
    0.36
     gurus
    0.36
     ಸದ
    0.35
    शनल
    0.34
    zingen
    0.34
    Activations Density 0.000%

    No Known Activations