© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205481
    Prev
    Next
    INDEX
    Explanations

    government and organizational structures

    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_25_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
    ሬ
    0.32
     영상을
    0.31
    擞
    0.31
    дим
    0.30
    astaan
    0.30
    楼
    0.30
    ógł
    0.30
     playerCount
    0.29
    ˶
    0.29
    roduction
    0.29
    POSITIVE LOGITS
     etc
    0.34
     proposing
    0.32
     only
    0.31
     Board
    0.31
     payable
    0.30
    avits
    0.30
     carbonates
    0.29
     ongoing
    0.29
     solely
    0.29
     enrichment
    0.28
    Activations Density 0.002%

    No Known Activations