© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 38-GEMMASCOPE-2-TRANSCODER-262K
    4. 204
    Prev
    Next
    INDEX
    Explanations

    CPU usage and time

    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_38_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
     viewModel
    0.44
     mater
    0.38
     alumina
    0.37
    ueill
    0.37
     Aachen
    0.36
     न
    0.36
     klare
    0.35
     MATERIAL
    0.34
    畯
    0.34
    ريح
    0.33
    POSITIVE LOGITS
     p
    0.40
     হাইকমিশনার
    0.39
     Hasta
    0.37
    Encom
    0.37
     Até
    0.37
     เหน
    0.37
    殡
    0.36
    ilot
    0.35
     daddy
    0.34
    გან
    0.34
    Activations Density 0.015%

    No Known Activations