© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138596
    Prev
    Next
    INDEX
    Explanations

    typing on tables

    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_12_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
    的
    0.52
     not
    0.51
     বড়
    0.51
     le
    0.47
    ;</
    0.46
    瘴
    0.46
    大的
    0.44
     বড়
    0.44
     ini
    0.44
     ле
    0.43
    POSITIVE LOGITS
     olid
    0.49
     نیند
    0.48
     classi
    0.48
     emblematic
    0.47
     হামলার
    0.46
     quizz
    0.46
     neoplasms
    0.45
     diplomas
    0.45
    تری
    0.45
    ڻ
    0.45
    Activations Density 0.001%

    No Known Activations