© 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. 197273
    Prev
    Next
    INDEX
    Explanations

    CREATE DATABASE

    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
     coldest
    0.43
    壁
    0.43
    ГА
    0.41
    CLIP
    0.41
     sosten
    0.40
     IUser
    0.39
    庐
    0.39
    凖
    0.38
    تبار
    0.38
     Ï
    0.38
    POSITIVE LOGITS
     Harga
    0.47
     unable
    0.46
     kunci
    0.45
    uto
    0.43
     predators
    0.42
     berupa
    0.42
     shortcomings
    0.41
     mantan
    0.41
     ooz
    0.41
     disorders
    0.40
    Activations Density 0.001%

    No Known Activations