© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136889
    Prev
    Next
    INDEX
    Explanations

    failures related to maintenance

    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_37_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
     Бере
    0.42
     Medizin
    0.40
    lir
    0.37
    íf
    0.37
    acije
    0.36
    toxic
    0.36
     Toxic
    0.36
    笔
    0.36
     kurang
    0.36
     Formal
    0.35
    POSITIVE LOGITS
     maintenance
    0.59
     drivetrain
    0.57
     maint
    0.51
     onboard
    0.51
     powertrain
    0.51
     repair
    0.50
     upkeep
    0.48
     mainten
    0.47
     driv
    0.46
     wrench
    0.46
    Activations Density 0.000%

    No Known Activations