© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78190
    Prev
    Next
    INDEX
    Explanations

    approximately

    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_31_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
    掍
    0.40
    প্রিল
    0.39
    gebn
    0.37
     의해
    0.35
     производителей
    0.35
     Ganz
    0.33
    驿
    0.33
     promis
    0.33
     의한
    0.33
    Science
    0.33
    POSITIVE LOGITS
     wynosi
    0.43
     mellom
    0.39
    售
    0.39
     noin
    0.39
     सल्
    0.39
    identité
    0.38
    generational
    0.38
    InterfaceLine
    0.38
     brut
    0.37
     salmon
    0.37
    Activations Density 0.025%

    No Known Activations