© 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. 6822
    Prev
    Next
    INDEX
    Explanations

    lines of code that import java packages

    oai_token-act-pair · gemini-2.0-flash

    technical terms and Java imports

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

    say dot

    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
    !
    -0.59
    ↵
    -0.57
    ↵↵
    -0.56
    (
    -0.56
    nicki
    -0.55
     .
    -0.54
    ?
    -0.52
    .,
    -0.52
     
    -0.52
     sóc
    -0.50
    POSITIVE LOGITS
     الحره
    1.05
     فريبيس
    0.88
     itſelf
    0.88
     EconPapers
    0.84
    MemoryWarning
    0.80
    يميديا
    0.75
    Rujuakan
    0.74
     незавершена
    0.73
    WebVitals
    0.70
    )_/¯
    0.70
    Activations Density 1.051%

    No Known Activations