© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 11018
    Prev
    Next
    INDEX
    Explanations

    text describing government or organizational structures

    oai_token-act-pair · gemini-2.0-flash

    Legal and official information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    OGND
    -0.56
    findpost
    -0.52
     voks
    -0.50
     Cum
    -0.50
     planas
    -0.49
     gius
    -0.48
    ordinaire
    -0.47
    nsyn
    -0.47
     채
    -0.47
    期刊论文
    -0.46
    POSITIVE LOGITS
    enderror
    0.62
    IVEREF
    0.60
    WebVitals
    0.58
    FormTagHelper
    0.57
     оригіналу
    0.57
    AnchorTagHelper
    0.57
    RegistryLite
    0.57
    oredCriteria
    0.56
    PRNewswire
    0.55
    Zend
    0.54
    Activations Density 0.636%

    No Known Activations