© 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. 10468
    Prev
    Next
    INDEX
    Explanations

    comma followed by and

    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
     chatId
    0.43
     Zack
    0.41
     seng
    0.41
    薄
    0.41
     ಭ
    0.40
     薄
    0.39
     বিজ্ঞান
    0.39
    ارق
    0.39
     arrend
    0.39
     깔
    0.39
    POSITIVE LOGITS
    뚤
    0.38
    тивних
    0.37
     Hof
    0.36
    шою
    0.35
     uncovering
    0.34
     transference
    0.34
    尻
    0.34
     disclosing
    0.34
     valuing
    0.34
     People
    0.34
    Activations Density 0.002%

    No Known Activations