© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51652
    Prev
    Next
    INDEX
    Explanations

    introductions like "Dr." or "Sarah:"

    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_31_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
    ギー
    0.40
    Secondary
    0.39
    ②
    0.38
    primer
    0.38
     secondary
    0.38
    奢侈
    0.37
    நக
    0.36
    SECONDARY
    0.36
    inggi
    0.36
     authority
    0.36
    POSITIVE LOGITS
    matplotlib
    0.37
     matplotlib
    0.37
    ovariant
    0.37
    attup
    0.36
     বাং
    0.36
    督
    0.36
    鐫
    0.36
     Mali
    0.35
     түр
    0.34
     captioned
    0.33
    Activations Density 0.005%

    No Known Activations