© 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. 29637
    Prev
    Next
    INDEX
    Explanations

    high quality

    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
     держави
    0.38
     chin
    0.38
    긍
    0.37
     loafers
    0.36
     SIZE
    0.36
     Neck
    0.36
    ೃತ
    0.35
    :%
    0.35
     fined
    0.35
    جیب
    0.35
    POSITIVE LOGITS
    Closed
    0.49
     Closed
    0.42
    closed
    0.42
    Deep
    0.41
    Quality
    0.40
    Обра
    0.40
     closed
    0.40
    Mobile
    0.40
     qualidade
    0.40
    Фор
    0.39
    Activations Density 0.005%

    No Known Activations