© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155088
    Prev
    Next
    INDEX
    Explanations

    buses

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Salah
    0.44
    এস
    0.40
     Salah
    0.39
    coat
    0.37
     SAS
    0.36
     assolutamente
    0.36
    ोत्
    0.36
     佐
    0.36
    SAS
    0.36
     assertEquals
    0.35
    POSITIVE LOGITS
     bus
    1.31
    bus
    1.24
    Bus
    1.20
     Bus
    1.17
     buses
    1.10
     busses
    1.09
    BUS
    1.07
     buss
    1.01
     BUS
    0.98
     Buses
    0.93
    Activations Density 0.000%

    No Known Activations