© 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
    2. Gemma-3-27B-IT
    3. 29-GEMMASCOPE-2-TRANSCODER-262K
    4. 180643
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_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
     ####
    0.39
    でもある
    0.38
    HashSet
    0.36
    عات
    0.36
    ipher
    0.36
    #
    0.36
     گیا
    0.35
    集合
    0.35
    ####
    0.34
    ᒐ
    0.34
    POSITIVE LOGITS
    觡
    0.41
    čných
    0.37
     заб
    0.36
    neg
    0.35
    jších
    0.35
    ্কৃতিক
    0.35
    듦
    0.35
    craft
    0.35
    徂
    0.34
     discriminating
    0.34
    Activations Density 0.000%

    No Known Activations