© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201623
    Prev
    Next
    INDEX
    Explanations

    Spark

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     índice
    0.45
    werpen
    0.41
    omania
    0.41
     Spark
    0.40
     Sparks
    0.40
     पार्क
    0.39
    公园
    0.38
     П
    0.38
     spark
    0.37
     sparks
    0.37
    POSITIVE LOGITS
    Peng
    0.50
     MTL
    0.42
    Ownership
    0.40
    統合
    0.38
    Cor
    0.37
     నిర్
    0.37
    Serving
    0.37
    ื่อง
    0.37
    Bull
    0.37
    Tier
    0.36
    Activations Density 0.001%

    No Known Activations