© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4104
    Prev
    Next
    INDEX
    Explanations

    a mix of stop words "in, last", variable names with "result", location context "group, side" and names with "th, ndez", and sports teams with "madrid, sevilla".

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     jLabel
    -0.66
    Carriera
    -0.61
     WebDriverWait
    -0.58
    CompilerServices
    -0.58
    mybatisplus
    -0.57
    basicConfig
    -0.57
    Sucesor
    -0.55
    ectoria
    -0.55
     createState
    -0.50
    StreetMap
    -0.50
    POSITIVE LOGITS
    heça
    0.54
    цезда
    0.52
    entiation
    0.52
    そちら
    0.49
     case
    0.48
     Púb
    0.48
     nhiêu
    0.47
    SpringBootTest
    0.47
    Case
    0.47
     exécu
    0.46
    Activations Density 0.374%

    No Known Activations