© 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. 18015
    Prev
    Next
    INDEX
    Explanations

    Government Building

    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
     tower
    1.02
     Tower
    1.02
    Tower
    0.99
    tower
    0.86
    塔
    0.86
     torre
    0.79
     towers
    0.72
     Eiffel
    0.63
     Towers
    0.61
     Torre
    0.61
    POSITIVE LOGITS
    Ther
    0.38
     netto
    0.37
    urlencoded
    0.36
     nets
    0.36
    ranno
    0.36
     विनाश
    0.36
     ther
    0.36
     fiscale
    0.35
    滑
    0.35
     netting
    0.35
    Activations Density 0.034%

    No Known Activations