© 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. 3636
    Prev
    Next
    INDEX
    Explanations

    C++ code related to sending and receiving updates

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     number
    -3.03
    number
    -2.83
     Number
    -2.67
    Number
    -2.66
     NUMBER
    -2.55
    NUMBER
    -2.47
     numbers
    -2.36
     número
    -2.27
     num
    -2.11
     Numbers
    -2.09
    POSITIVE LOGITS
    通販
    0.45
    ãi
    0.42
    SpringBootTest
    0.42
     متعلقه
    0.40
    клопе
    0.40
    lacable
    0.39
    >())
    0.39
    |()
    0.39
    bierz
    0.38
    piecze
    0.37
    Activations Density 0.693%

    No Known Activations