Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 9990
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with the Fukushima nuclear disaster and its aftermath.

    oai_token-act-pair · gemini-2.0-flash

    Japan

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Paused
    -0.47
    principalTable
    -0.47
    SPJ
    -0.44
    StoryboardSegue
    -0.43
    ANTLR
    -0.42
    XmlAccessorType
    -0.42
    bral
    -0.42
    XmlType
    -0.39
    XmlSchema
    -0.39
     متعلقه
    -0.39
    POSITIVE LOGITS
     Japan
    0.85
     JAPAN
    0.82
     Tokyo
    0.77
    Japan
    0.77
    JAPAN
    0.74
    japan
    0.74
     TOKYO
    0.73
     Japanese
    0.71
     Anime
    0.70
     Jepang
    0.70
    Activations Density 1.507%

    No Known Activations