© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4496
    Prev
    Next
    INDEX
    Explanations

    words associated with conflict, especially regarding characters and politics

    oai_token-act-pair · gemini-2.0-flash

    personal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     viime
    -0.43
    ļi
    -0.42
    mės
    -0.42
    asius
    -0.41
     lopp
    -0.40
     julk
    -0.40
    ece
    -0.40
    multicolumn
    -0.39
     ģ
    -0.38
     Ehe
    -0.38
    POSITIVE LOGITS
    DockStyle
    0.94
     estimés
    0.88
    twimg
    0.84
     كومونز
    0.81
    出版年
    0.81
    jsxFileName
    0.75
     Wiktionnaire
    0.75
     estekak
    0.74
    قایناق‌لار
    0.74
     surla
    0.74
    Activations Density 2.622%

    No Known Activations