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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16183
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to paganism, especially Wicca, Druids, and associated celebrations

    oai_token-act-pair · gemini-2.0-flash

    equinox

    np_max-act · gemini-2.0-flash

    equinox

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.20
    '
    -0.78
    .
    -0.73
    ’
    -0.70
    \{\\
    -0.68
    Vendo
    -0.63
    在
    -0.63
    protoimpl
    -0.62
    Искәрмәләр
    -0.62
    ,
    -0.62
    POSITIVE LOGITS
    s
    1.30
    ."</
    0.91
     TAMBÉM
    0.90
    جوايز
    0.87
    sing
    0.85
    sä
    0.85
     alamu
    0.82
    sko
    0.81
    sted
    0.80
    sen
    0.79
    Activations Density 17.726%

    No Known Activations