© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 59451
    Prev
    Next
    INDEX
    Explanations

    table creation or reference

    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_11_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
     Otra
    0.32
    p
    0.32
    ison
    0.32
     ])
    0.31
    colorize
    0.31
    unehmen
    0.31
     G
    0.30
    another
    0.29
    ඨ
    0.29
     Г
    0.29
    POSITIVE LOGITS
     variétés
    0.31
     package
    0.30
    کا
    0.29
     Classics
    0.27
    ด
    0.26
    便
    0.25
     Cybersecurity
    0.25
    не
    0.25
     Applications
    0.25
    صبح
    0.25
    Activations Density 0.022%

    No Known Activations