© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45553
    Prev
    Next
    INDEX
    Explanations

    local SparkContext

    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
    ᡤ
    0.31
     ursprüng
    0.29
    Ẵ
    0.27
    樀
    0.27
     শতা
    0.27
     zatem
    0.27
     বাসিন্দা
    0.26
     బా
    0.25
     aasta
    0.25
    鸦
    0.25
    POSITIVE LOGITS
    为了
    0.30
    Follow
    0.29
    สำหรับ
    0.29
    Needed
    0.28
    heed
    0.28
    Before
    0.27
    for
    0.27
     hym
    0.27
    Untuk
    0.26
    ભગ
    0.26
    Activations Density 0.002%

    No Known Activations