© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225831
    Prev
    Next
    INDEX
    Explanations

    street names

    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_10_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
    كين
    0.73
    ቂያ
    0.70
     كيفية
    0.69
    宪
    0.66
    كيت
    0.66
    ك
    0.64
    ريف
    0.64
    য়ে
    0.62
     ataque
    0.61
    رويج
    0.61
    POSITIVE LOGITS
     Street
    0.90
     street
    0.88
    с
    0.84
     Road
    0.79
    streets
    0.78
     Avenue
    0.77
    t
    0.77
     Boulevard
    0.76
     Streets
    0.74
    Street
    0.73
    Activations Density 0.013%

    No Known Activations