© 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. 2374
    Prev
    Next
    INDEX
    Explanations

    final answer: box

    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
     malonyl
    0.42
    兄
    0.41
     मंत्रिम
    0.40
     χρόνο
    0.37
     mingling
    0.37
    stargo
    0.37
    犮
    0.37
     отделения
    0.37
    స్సు
    0.37
     Pelham
    0.37
    POSITIVE LOGITS
     ਜ਼
    0.36
    ogh
    0.36
    円
    0.36
    hon
    0.35
     fund
    0.35
    +(
    0.34
     apost
    0.33
    owness
    0.33
    +(\
    0.33
     inscr
    0.33
    Activations Density 0.004%

    No Known Activations