© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13252
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate something is worthwhile

    oai_token-act-pair · gemini-2.0-flash

    worth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     CreateTagHelper
    -0.94
    ImageContext
    -0.79
    ScopeManager
    -0.79
    protoimpl
    -0.76
    XmlAccessType
    -0.71
    ########.
    -0.70
    endphp
    -0.70
    Datuak
    -0.68
     FetchType
    -0.68
     Normdatei
    -0.66
    POSITIVE LOGITS
    while
    1.00
     while
    0.94
     While
    0.76
    WHILE
    0.73
    While
    0.71
     mentre
    0.70
     WHILE
    0.69
     enquanto
    0.65
     whereas
    0.63
    mientras
    0.63
    Activations Density 1.193%

    No Known Activations