© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 5696
    Prev
    Next
    INDEX
    Explanations

    read or recv

    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
    adə
    0.43
    query
    0.41
     Filosof
    0.39
     tumb
    0.38
    weiler
    0.36
    ㅌ
    0.36
     obtaining
    0.36
    哲学
    0.36
    얻
    0.36
     Signs
    0.35
    POSITIVE LOGITS
     read
    0.68
     recv
    0.61
    read
    0.61
     Read
    0.57
    recv
    0.57
    ReadLine
    0.56
     readline
    0.56
    Read
    0.55
    readline
    0.55
     خوان
    0.51
    Activations Density 0.011%

    No Known Activations