© 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. 140361
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    爭
    0.38
     Brahm
    0.36
     Fibonacci
    0.35
    ษย์
    0.35
     leading
    0.35
     দীননাথ
    0.34
    ्तर
    0.34
    รั่ง
    0.34
    matical
    0.34
     XI
    0.34
    POSITIVE LOGITS
    @
    0.35
     alterações
    0.32
    そんな
    0.31
    ＠
    0.30
    Adventure
    0.30
    changes
    0.30
     непри
    0.30
     acidification
    0.30
    这样一个
    0.30
    [:
    0.30
    Activations Density 0.005%

    No Known Activations