© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77899
    Prev
    Next
    INDEX
    Explanations

    data collection and preparation

    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
     latch
    0.43
     মতি
    0.42
     lat
    0.41
    UpdateButton
    0.38
     ৩৪
    0.38
     आर्ट
    0.38
    AKI
    0.38
    转
    0.38
     దక్షిణ
    0.37
     H
    0.37
    POSITIVE LOGITS
     porridge
    0.40
     könnten
    0.38
    classname
    0.37
    CellValue
    0.37
    ándola
    0.37
     जोशी
    0.37
    ющегося
    0.36
     ऑपरेटिंग
    0.35
    instrList
    0.34
    ев
    0.34
    Activations Density 0.145%

    No Known Activations