© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6639
    Prev
    Next
    INDEX
    Explanations

    print_board

    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_40_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
    仞
    0.39
    शासित
    0.38
    သိ
    0.38
    䐝
    0.38
     baths
    0.37
    violations
    0.37
    计
    0.37
     ownership
    0.37
     계
    0.37
    ीण
    0.37
    POSITIVE LOGITS
    Thrown
    0.36
     Discrete
    0.35
     topo
    0.35
     assimilate
    0.35
    隔離
    0.34
     Lyme
    0.34
     Astral
    0.34
     Astr
    0.34
    ENA
    0.34
     Huxley
    0.34
    Activations Density 0.001%

    No Known Activations