© 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. 4598
    Prev
    Next
    INDEX
    Explanations

    words relating to aristocracy, royalty, and high-ranking individuals.

    oai_token-act-pair · gemini-2.0-flash

    Historical names

    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
     CURLOPT
    -0.49
     Himo
    -0.48
     juges
    -0.42
    Rhestr
    -0.40
    Бахар
    -0.40
    lawayo
    -0.39
     Meksiku
    -0.39
     BoxDecoration
    -0.39
     تانيه
    -0.39
     FetchType
    -0.38
    POSITIVE LOGITS
     Charlemagne
    0.88
     Etrus
    0.79
     Molière
    0.75
     Frenchmen
    0.75
     Bacchus
    0.74
     Tacitus
    0.74
     Florentine
    0.74
     Dionys
    0.73
     Claudius
    0.72
     Josephus
    0.72
    Activations Density 77.490%

    No Known Activations