© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136157
    Prev
    Next
    INDEX
    Explanations

    for iteration

    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_37_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
     sake
    0.50
     purposes
    0.47
    NEED
    0.38
    这件事
    0.38
    ”;
    0.38
     Sake
    0.38
     linguistic
    0.37
     lung
    0.36
     Purposes
    0.36
     konsep
    0.36
    POSITIVE LOGITS
    ▀
    0.40
    ITLE
    0.40
    Ru
    0.37
    ެއް
    0.37
     Rü
    0.37
    ರೂ
    0.37
    Watcher
    0.37
     სახელ
    0.37
    SOs
    0.35
     Ruhe
    0.34
    Activations Density 0.002%

    No Known Activations