© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11786
    Prev
    Next
    INDEX
    Explanations

    price goes up

    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
    ف
    0.28
    ار
    0.24
    ோட
    0.24
    কোন
    0.23
    ابقات
    0.23
    к
    0.23
    ک
    0.22
    ע
    0.22
    is
    0.22
    ol
    0.22
    POSITIVE LOGITS
     changed
    0.33
     berubah
    0.29
     grumpy
    0.28
     Changed
    0.27
     but
    0.27
     maar
    0.26
    ”，
    0.26
     maravill
    0.26
     meandering
    0.26
     পরিবর্তিত
    0.26
    Activations Density 0.002%

    No Known Activations