© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2537
    Prev
    Next
    INDEX
    Explanations

    Material Design components and principles

    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_39_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
    ervice
    0.44
    អង្
    0.38
     роли
    0.38
    讴
    0.38
     honour
    0.37
     Nixon
    0.37
    機構
    0.37
    Ing
    0.35
    工程
    0.35
    honor
    0.35
    POSITIVE LOGITS
     परफेक्ट
    0.39
     baseline
    0.39
    कट
    0.37
    晉
    0.37
     jay
    0.37
     shaping
    0.36
    jay
    0.36
     staffed
    0.36
    sser
    0.36
     perfetta
    0.36
    Activations Density 0.006%

    No Known Activations