© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195863
    Prev
    Next
    INDEX
    Explanations

    navigating software tab menus

    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_26_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
     bauen
    0.41
     kumpulan
    0.41
     অংশ
    0.40
     kelompok
    0.40
     definida
    0.40
    飾り
    0.40
     esperienze
    0.40
    >[</
    0.39
    лды
    0.39
     accessori
    0.39
    POSITIVE LOGITS
     logistical
    0.38
     જતા
    0.37
     wouldn
    0.37
     Schedules
    0.37
     झाल्यावर
    0.36
    的第一
    0.34
    configurable
    0.34
     moral
    0.34
     wild
    0.34
    ular
    0.33
    Activations Density 0.003%

    No Known Activations