© 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. 12379
    Prev
    Next
    INDEX
    Explanations

    code comments that include author and creation date information

    oai_token-act-pair · gemini-2.0-flash

    programming keywords or author-related identifiers

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

    author, by

    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
     insuffisamment
    -0.76
    ագրություններ
    -0.68
    SourceChecksum
    -0.58
    setVerticalGroup
    -0.57
    findpost
    -0.55
     EconPapers
    -0.55
     مشين
    -0.55
    DockStyle
    -0.54
     Contactez
    -0.51
    Kaynakça
    -0.50
    POSITIVE LOGITS
    MethodManager
    0.61
    線が
    0.49
    epam
    0.49
    gesetzt
    0.48
     tartalomajánló
    0.48
    RetentionPolicy
    0.48
    लाइन
    0.47
    tacle
    0.46
    LElement
    0.46
    nically
    0.46
    Activations Density 1.789%

    No Known Activations