© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 1126
    Prev
    Next
    INDEX
    Explanations

    seemingly random numbers and characters that could be IDs, references, catalog numbers, etc

    oai_token-act-pair · gemini-2.0-flash

    Scientific references and numbers

    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
    CloseOperation
    -0.63
    CJK
    -0.55
    ‍
    -0.50
    adze
    -0.48
    Linq
    -0.48
    HttpFoundation
    -0.48
    庁
    -0.48
    Six
    -0.47
    кол
    -0.47
    InjectMocks
    -0.47
    POSITIVE LOGITS
    IndentedString
    0.88
     itſelf
    0.80
    styleType
    0.75
     AssemblyCulture
    0.71
     TextAlign
    0.69
    MessageTagHelper
    0.69
     InputDecoration
    0.68
     fufficient
    0.66
     cdti
    0.64
     referenties
    0.63
    Activations Density 5.113%

    No Known Activations