© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174746
    Prev
    Next
    INDEX
    Explanations

    your

    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_20_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
    磵
    0.31
    STRACT
    0.28
     Особенно
    0.27
    MakeRect
    0.26
     Özellikle
    0.26
     ஒ
    0.26
     سوف
    0.25
     Đặc
    0.25
     Makarna
    0.25
     Membuat
    0.24
    POSITIVE LOGITS
    Ки
    0.27
     pół
    0.26
    தல
    0.26
    मो
    0.26
    क
    0.26
     kamm
    0.25
     precis
    0.25
     संक्षिप्त
    0.25
     bowiem
    0.25
     editions
    0.25
    Activations Density 0.045%

    No Known Activations