© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203595
    Prev
    Next
    INDEX
    Explanations

    include details or examples

    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_6_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
    س
    2.05
    ق
    1.80
    م
    1.55
    ش
    1.51
    ج
    1.49
    خ
    1.45
    स
    1.43
    ن
    1.34
    ع
    1.34
    ت
    1.34
    POSITIVE LOGITS
    ៥
    0.87
     ?”
    0.80
    𝚆
    0.76
    LEASE
    0.76
    ⁵
    0.75
    ૭
    0.73
     \%)$
    0.73
    dDays
    0.72
     Hochzeit
    0.72
    nashvillehousing
    0.71
    Activations Density 0.003%

    No Known Activations