© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 148904
    Prev
    Next
    INDEX
    Explanations

    word beginnings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    UX
    0.45
    U
    0.43
    u
    0.41
    ux
    0.40
     hæ
    0.38
    evice
    0.38
     vess
    0.37
     essentielles
    0.37
    NDE
    0.36
     sensor
    0.36
    POSITIVE LOGITS
    婁
    0.39
    제목
    0.37
     mow
    0.37
    или
    0.36
    まぁ
    0.36
    Nicholas
    0.35
    옵
    0.35
     дистан
    0.35
    ılığı
    0.34
     Ethnicity
    0.34
    Activations Density 0.000%

    No Known Activations