© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163425
    Prev
    Next
    INDEX
    Explanations

    You do something

    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_31_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
    ayutt
    0.38
     तथ
    0.35
     Джу
    0.33
    ocols
    0.33
     contradictions
    0.33
     خاصيه
    0.33
    伦
    0.32
    UserRootDir
    0.31
    ทัน
    0.31
    żd
    0.31
    POSITIVE LOGITS
     Gotta
    0.39
    ிலான
    0.39
     അല്ല
    0.38
     ringan
    0.37
     menjadi
    0.36
     penting
    0.36
     gotta
    0.36
    --){
    0.35
     indenture
    0.35
     saldo
    0.34
    Activations Density 0.013%

    No Known Activations