© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 33820
    Prev
    Next
    INDEX
    Explanations

    air traffic management

    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_31_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
    جاد
    0.42
    сим
    0.38
     Kumari
    0.38
     হাত
    0.38
     MJ
    0.38
     Narc
    0.36
    તાં
    0.36
    薪
    0.36
    濵
    0.36
    TakePhoto
    0.34
    POSITIVE LOGITS
    undra
    0.42
     Slot
    0.40
     pendekatan
    0.40
     слот
    0.40
     ব্রাহ্মণ
    0.39
    melody
    0.37
     testicular
    0.36
    studded
    0.36
    Lung
    0.36
     Verona
    0.35
    Activations Density 0.033%

    No Known Activations