© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91845
    Prev
    Next
    INDEX
    Explanations

    message type and format definitions

    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
    laser
    0.59
    kaisi
    0.57
    ↵↵↵↵↵
    0.56
    cf
    0.56
    up
    0.56
    ləşdirilib
    0.55
     После
    0.54
     頭
    0.54
    ’),
    0.54
    лет
    0.54
    POSITIVE LOGITS
    νου
    0.52
    Emulator
    0.51
    PHONE
    0.50
    ዛት
    0.50
    ů
    0.49
    če
    0.48
    wali
    0.48
    یں۔
    0.48
     leven
    0.48
     microphones
    0.48
    Activations Density 0.000%

    No Known Activations