© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260738
    Prev
    Next
    INDEX
    Explanations

    takeoff and landing

    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_22_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
     nghiệp
    0.28
     congregate
    0.27
     thereafter
    0.27
    业
    0.27
     Lebanon
    0.26
     Roosevelt
    0.26
     reuni
    0.26
     sinist
    0.25
     logon
    0.25
     Toledo
    0.25
    POSITIVE LOGITS
     مَا
    0.30
    Якщо
    0.30
    ників
    0.30
     articolo
    0.30
    𝗷
    0.29
    Ֆ
    0.29
    writers
    0.28
    QUANT
    0.27
    ൪
    0.27
     plabic
    0.27
    Activations Density 0.000%

    No Known Activations