© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2978
    Prev
    Next
    INDEX
    Explanations

    crossing roads or streets

    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
    Mau
    0.42
     நகர
    0.40
     Mau
    0.39
     cytoplasm
    0.36
    ঁ
    0.36
    uč
    0.36
     উপকূল
    0.35
     Mauro
    0.35
     판
    0.35
     Gauge
    0.34
    POSITIVE LOGITS
     road
    1.63
    road
    1.34
    Road
    1.34
     roads
    1.32
     ROAD
    1.27
     Road
    1.26
    道路
    1.20
    ROAD
    1.20
     सड़क
    1.16
    roads
    1.13
    Activations Density 0.048%

    No Known Activations