© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12039
    Prev
    Next
    INDEX
    Explanations

    Header followed by parenthesis

    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_13_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
    आ
    0.53
     ABI
    0.51
     Yus
    0.49
    身影
    0.49
    （
    0.48
    יום
    0.47
    י
    0.46
    таў
    0.46
    脚
    0.46
     predecessor
    0.45
    POSITIVE LOGITS
    %}
    0.57
    closes
    0.52
    me
    0.49
    PlayerDataCache
    0.48
    crever
    0.48
     ストレ
    0.47
    ép
    0.47
    éviter
    0.46
    ко
    0.46
    Capricorn
    0.46
    Activations Density 0.002%

    No Known Activations