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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28538
    Prev
    Next
    INDEX
    Explanations

    content within brackets

    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
     há
    0.37
    產
    0.37
    产
    0.36
     produce
    0.35
    produ
    0.35
    rol
    0.33
     कटो
    0.33
    gro
    0.33
     PRODU
    0.32
    妬
    0.32
    POSITIVE LOGITS
    篮
    0.41
    钰
    0.37
     Resolve
    0.37
     menyelesaikan
    0.36
     मीन
    0.36
     ফিরে
    0.35
     Successful
    0.35
     डिजिट
    0.35
     Meaning
    0.35
     Buildable
    0.35
    Activations Density 0.000%

    No Known Activations