© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10186
    Prev
    Next
    INDEX
    Explanations

    Police, login, legal, customs

    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
     মাইক্র
    0.46
    微
    0.40
     microstructure
    0.40
    Cm
    0.40
    Micro
    0.39
    helix
    0.39
    स्थिति
    0.38
     принято
    0.38
     외국
    0.38
    MICRO
    0.38
    POSITIVE LOGITS
     HOT
    0.48
     hot
    0.47
     Hot
    0.44
    ▆
    0.42
     OFFICES
    0.39
     offices
    0.37
    োস
    0.37
    тере
    0.36
     dodge
    0.36
     dodging
    0.36
    Activations Density 0.008%

    No Known Activations