© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106257
    Prev
    Next
    INDEX
    Explanations

    Xishuangbanna, Yunnan, China

    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_1_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
    ↵
    1.95
    y
    1.38
    u
    1.33
    k
    1.30
    ก
    1.30
    í
    1.20
    ü
    1.19
    ing
    1.14
    </h3>
    1.12
    ↵↵
    1.10
    POSITIVE LOGITS
    ка
    1.50
    し
    1.46
    ۲
    1.17
     éléments
    1.10
    dois
    1.09
     homologs
    1.08
    رک
    1.07
    ciamo
    1.06
    là
    1.05
    ご
    1.05
    Activations Density 0.000%

    No Known Activations