© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6551
    Prev
    Next
    INDEX
    Explanations

    references to figures and tables, likely in research papers

    oai_token-act-pair · gemini-2.0-flash

    programming language tokens or keywords

    np_token-act-pair-logits · gpt-4o-mini

    identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    kowitz
    -0.50
     Friday
    -0.48
     сказал
    -0.47
     сказала
    -0.47
    desh
    -0.46
     T
    -0.46
    幸いです
    -0.45
     Saturday
    -0.45
     M
    -0.45
     */
    -0.44
    POSITIVE LOGITS
    aarrggbb
    1.20
    parsedMessage
    1.05
    Sucesor
    0.95
    expandindo
    0.92
    הערות
    0.92
    TagMode
    0.90
    QMetaType
    0.90
    
    0.88
    ContentAsync
    0.88
    脚注の使い方
    0.87
    Activations Density 11.307%

    No Known Activations