© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4707
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    オブジェクト
    0.39
     oggetti
    0.38
    物件
    0.37
     объекты
    0.37
     объекта
    0.37
     objets
    0.36
    emporal
    0.36
    贍
    0.35
     خون
    0.35
     দ্রব্য
    0.35
    POSITIVE LOGITS
     pointer
    0.36
     free
    0.35
    ptr
    0.35
     ptr
    0.35
    pointer
    0.34
     pointers
    0.33
     value
    0.32
     extern
    0.32
     pow
    0.32
    cast
    0.32
    Activations Density 0.070%

    No Known Activations