© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10687
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words around them, particularly when they are related to authority or possible crime

    oai_token-act-pair · gemini-2.0-flash

    Swaziland news

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    loon
    -0.50
    jsonwebtoken
    -0.49
    omla
    -0.48
    TintMode
    -0.47
    TypedDataSet
    -0.47
     doPost
    -0.47
    listdir
    -0.47
     MessageBoxIcon
    -0.46
    WebElementEntity
    -0.45
    ().__
    -0.45
    POSITIVE LOGITS
    انيف
    0.58
    />";
    0.55
     fourrure
    0.54
    WriteAttribute
    0.54
    зец
    0.53
    '/>
    0.52
     تانيه
    0.51
    ionales
    0.51
     poursuite
    0.50
     vicenda
    0.50
    Activations Density 0.297%

    No Known Activations