© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35982
    Prev
    Next
    INDEX
    Explanations

    silica (SiO2)

    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_3_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
    은
    0.61
    습니다
    0.60
     시간을
    0.60
    지만
    0.59
    ᱞ
    0.59
    مج
    0.59
     계
    0.58
    ম্ব
    0.58
    랑
    0.57
    𝚋
    0.56
    POSITIVE LOGITS
     for
    0.68
     livre
    0.64
     lop
    0.63
     fio
    0.63
     by
    0.59
     lym
    0.59
     marm
    0.59
     garanti
    0.59
     iod
    0.58
     morg
    0.58
    Activations Density 0.001%

    No Known Activations