© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196882
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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_26_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
    ၷ
    0.42
    рак
    0.39
    Minecraft
    0.38
     непре
    0.37
    лли
    0.37
    KeyboardMarkup
    0.37
     envió
    0.36
    மைய
    0.36
    ieszcz
    0.35
     invariable
    0.35
    POSITIVE LOGITS
    倒是
    0.40
    เลย
    0.39
     рублей
    0.38
     ফলে
    0.38
     then
    0.37
     />;
    0.36
    เส้น
    0.36
    そして
    0.36
     লম্বা
    0.36
     তম
    0.35
    Activations Density 0.003%

    No Known Activations