© 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. 306
    Prev
    Next
    INDEX
    Explanations

    Tokyo and its districts

    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
    ambat
    0.41
    ExposureTime
    0.41
     Ukraj
    0.38
     uk
    0.37
     FAIL
    0.36
    AUC
    0.36
    睚
    0.36
     CZ
    0.36
    স্তার
    0.36
     contrario
    0.36
    POSITIVE LOGITS
     Tokyo
    0.71
    東京都
    0.66
    Tokyo
    0.64
     Governor
    0.51
     東京
    0.51
    东京
    0.51
     東京都
    0.50
     Osaka
    0.50
    東京
    0.50
    tok
    0.48
    Activations Density 0.045%

    No Known Activations