© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139451
    Prev
    Next
    INDEX
    Explanations

    SRS, clinic, Ger, trade, treatment

    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_12_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
    I
    0.39
    开始
    0.36
    atsioon
    0.36
    Wij
    0.36
     प्रथ
    0.36
    ską
    0.35
    withProperties
    0.35
    维
    0.34
    achusetts
    0.34
    Ik
    0.34
    POSITIVE LOGITS
    荲
    0.35
     o
    0.35
     stump
    0.35
     defying
    0.34
     وهم
    0.34
     fo
    0.33
     pese
    0.33
    м
    0.33
     defiance
    0.33
     só
    0.32
    Activations Density 0.001%

    No Known Activations