© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13897
    Prev
    Next
    INDEX
    Explanations

    date formats

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     winter
    -0.60
     اط
    -0.50
    期刊论文
    -0.49
     Winter
    -0.48
    Winter
    -0.48
    URLException
    -0.47
    kozá
    -0.47
    winter
    -0.46
    tens
    -0.45
    kym
    -0.45
    POSITIVE LOGITS
    '])){
    0.70
    
    0.65
    InSection
    0.65
    SceneManagement
    0.62
    "],
    0.62
    "},
    0.60
    "]
    0.60
     мәкалә
    0.59
    />";
    0.58
    reactstrap
    0.58
    Activations Density 1.174%

    No Known Activations