© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136952
    Prev
    Next
    INDEX
    Explanations

    The Guardian, Hindu, People, Morning Post

    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_37_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
     Watch
    0.44
    Watch
    0.42
    ]')
    0.41
     watch
    0.40
    Watcher
    0.40
     вули
    0.39
    𝕄
    0.39
     watching
    0.38
    なの
    0.37
    Annie
    0.37
    POSITIVE LOGITS
     Packages
    0.36
    DebugInformation
    0.35
    മുണ്ട്
    0.35
    urine
    0.33
    ','%
    0.33
    獻
    0.33
    %>
    0.33
     Facts
    0.33
    厚生
    0.33
    あまり
    0.32
    Activations Density 0.000%

    No Known Activations