© 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
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148751
    Prev
    Next
    INDEX
    Explanations

    USER

    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
     Dis
    0.49
    𝔀
    0.47
    R
    0.45
    悆
    0.40
    كن
    0.39
    мін
    0.39
    Dis
    0.38
     Side
    0.38
     disulfide
    0.38
     Decorated
    0.37
    POSITIVE LOGITS
    s
    0.70
    ی
    0.62
    ς
    0.58
    ы
    0.55
    schaft
    0.52
    ের
    0.51
     NAME
    0.48
    ों
    0.47
     Naam
    0.46
    sá
    0.46
    Activations Density 0.001%

    No Known Activations