© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4695
    Prev
    Next
    INDEX
    Explanations

    language in another language, possibly Chinese, that describes political power and control using strong, sometimes violent, imagery.

    oai_token-act-pair · gemini-2.0-flash

    code, other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.72
     Roskov
    -0.63
    matchCondition
    -0.62
    ГЛА
    -0.62
    ellido
    -0.62
    PageRoute
    -0.61
    webElementXpaths
    -0.60
     للاسماء
    -0.58
    Chham
    -0.57
    VersionUID
    -0.57
    POSITIVE LOGITS
    AnchorStyles
    0.52
     становника
    0.49
    ValueStyle
    0.47
    phol
    0.47
    IMENTS
    0.43
    quantum
    0.43
    Typing
    0.42
    EQUIPMENT
    0.41
    Manbalar
    0.40
    ρίζ
    0.40
    Activations Density 2.723%

    No Known Activations