© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 216376
    Prev
    Next
    INDEX
    Explanations

    percentages and figures

    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_16_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
    费
    0.19
    飨
    0.19
     Archived
    0.19
    的基础上
    0.18
    erzo
    0.18
    ධා
    0.18
    ർഡ്
    0.18
    عنی
    0.18
    ⼈
    0.18
    1
    0.18
    POSITIVE LOGITS
    sheets
    0.22
    漼
    0.21
     dampen
    0.21
     giác
    0.21
     oficinas
    0.21
     essences
    0.20
     tablespoons
    0.20
    \
    0.20
     mailbox
    0.20
     processo
    0.20
    Activations Density 0.011%

    No Known Activations