© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92126
    Prev
    Next
    INDEX
    Explanations

    railroads and railways

    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_11_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
    是什么
    0.28
     činjen
    0.27
     fakt
    0.27
    （
    0.27
    ；
    0.27
    ጨማሪ
    0.25
     Wochschr
    0.25
    。
    0.25
     polypes
    0.25
     Dhoni
    0.25
    POSITIVE LOGITS
    claiming
    0.29
    cerning
    0.29
     categorization
    0.29
     encompass
    0.28
    té
    0.28
     जुड़ा
    0.28
    taking
    0.27
     categorized
    0.27
     বিঘ
    0.27
    𝗹
    0.27
    Activations Density 0.000%

    No Known Activations