© 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. 202387
    Prev
    Next
    INDEX
    Explanations

    writing lines from streams

    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
     Persons
    0.46
     Subset
    0.43
     badger
    0.42
     Mikolai
    0.41
    oconvex
    0.41
     वैद्य
    0.40
    Persons
    0.38
     숨
    0.38
    गरी
    0.37
    addTarget
    0.37
    POSITIVE LOGITS
    znál
    0.40
    znego
    0.38
    swer
    0.35
     véh
    0.35
     задачи
    0.35
    応
    0.34
    咚
    0.34
     банк
    0.34
    льга
    0.34
    нного
    0.34
    Activations Density 0.000%

    No Known Activations