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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18361
    Prev
    Next
    INDEX
    Explanations

    Formula 1 teams and drivers

    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
     основу
    0.38
    ืม
    0.38
     contexts
    0.37
    獃
    0.37
     Nhật
    0.36
    Ụ
    0.36
    स्तव
    0.36
    获
    0.36
     ситуацию
    0.35
     conditionals
    0.35
    POSITIVE LOGITS
    iteness
    0.41
    Alberta
    0.39
     hud
    0.38
    Kur
    0.38
    Tracking
    0.38
    ्यवाद
    0.37
     Bahrain
    0.37
     Wanda
    0.37
     particolarmente
    0.37
     kic
    0.37
    Activations Density 0.012%

    No Known Activations