© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14704
    Prev
    Next
    INDEX
    Explanations

    trains and railways

    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_34_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
     Citizenship
    0.40
    䆔
    0.37
    globals
    0.37
     fêtes
    0.36
     transferência
    0.35
    Assertion
    0.35
    笈
    0.34
     politely
    0.34
     citizenship
    0.34
     orientación
    0.34
    POSITIVE LOGITS
     train
    1.00
     trains
    0.98
     railway
    0.97
     rail
    0.92
     Trains
    0.91
    train
    0.91
     Train
    0.91
    Trains
    0.90
     ferrovi
    0.90
    🚂
    0.89
    Activations Density 0.030%

    No Known Activations