© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198449
    Prev
    Next
    INDEX
    Explanations

    facts

    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
    結
    0.44
    ڏ
    0.43
    ふる
    0.39
    结
    0.36
    Shan
    0.35
    orda
    0.34
     ఇండి
    0.34
    lepiej
    0.34
    শ্র
    0.34
    /\/
    0.34
    POSITIVE LOGITS
     Kaz
    0.42
     contenant
    0.38
    द्योग
    0.37
     prawn
    0.37
    갯
    0.37
    סט
    0.37
     stocked
    0.37
    unsigned
    0.36
     risque
    0.36
    auche
    0.36
    Activations Density 0.001%

    No Known Activations