© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238612
    Prev
    Next
    INDEX
    Explanations

    match followed by parenthesis

    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_25_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
    原则
    0.43
     چکا
    0.43
    ПА
    0.40
    People
    0.39
     வெறும்
    0.39
    Balance
    0.39
    韵
    0.38
    ViewGroup
    0.38
    账户
    0.38
    壩
    0.38
    POSITIVE LOGITS
     scrap
    0.39
     prosecute
    0.39
     pak
    0.38
     innych
    0.38
     Anast
    0.38
     roasted
    0.38
    นาน
    0.38
    了一些
    0.38
     exposed
    0.37
    vento
    0.36
    Activations Density 0.000%

    No Known Activations