© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6617
    Prev
    Next
    INDEX
    Explanations

    Canadian things like Shield, Tire, National, Space

    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_40_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
     Presidents
    0.54
     الرئيس
    0.49
     President
    0.46
     ακ
    0.44
    㸽
    0.44
    mdp
    0.43
     राष्ट्रपति
    0.41
     Präsident
    0.40
     Zuma
    0.40
     ощу
    0.40
    POSITIVE LOGITS
     Tire
    0.40
     Shield
    0.36
    ADIAN
    0.36
     पड़
    0.35
    ስ
    0.35
     హె
    0.35
    ื่อย
    0.35
    පත්
    0.34
     Tho
    0.34
    CHAIN
    0.33
    Activations Density 0.023%

    No Known Activations