© 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. 209235
    Prev
    Next
    INDEX
    Explanations

    section introductions

    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
    ંચ
    0.24
    囷
    0.24
    revolution
    0.23
    责任
    0.23
    atted
    0.23
    uline
    0.22
     revolution
    0.22
    мера
    0.22
    etting
    0.21
    呓
    0.21
    POSITIVE LOGITS
     vali
    0.25
     tôi
    0.22
     leaped
    0.21
     भा
    0.21
     meines
    0.21
     leapt
    0.21
     pathologic
    0.21
     నాకు
    0.21
     యొక్క
    0.21
     ı
    0.20
    Activations Density 0.018%

    No Known Activations