© 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. 180799
    Prev
    Next
    INDEX
    Explanations

    code syntax and keywords

    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_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
     由
    0.27
    我和
    0.26
     публі
    0.24
     বণিক
    0.24
     একদিকে
    0.24
     слуша
    0.24
    炘
    0.24
     kesk
    0.23
     convinc
    0.23
     Бан
    0.23
    POSITIVE LOGITS
    if
    0.28
    į
    0.25
    xff
    0.24
    ini
    0.23
    cing
    0.23
    ']
    0.23
    _;
    0.23
     gemstones
    0.23
    jpg
    0.23
    this
    0.22
    Activations Density 0.005%

    No Known Activations