© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2019
    Prev
    Next
    INDEX
    Explanations

    the period character followed by a number

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    orative
    -0.62
     heapq
    -0.56
     otomatig
    -0.51
     FormData
    -0.51
    usepackage
    -0.48
    存于互联网档案馆
    -0.47
    SearchParams
    -0.47
     boleto
    -0.45
    modb
    -0.44
     BeautifulSoup
    -0.44
    POSITIVE LOGITS
    <bos>
    1.69
    ſelf
    0.54
    Personendaten
    0.53
    WireFormat
    0.51
     Савезне
    0.50
    ाहरण
    0.49
    RTLD
    0.48
    Всем
    0.47
    PyTuple
    0.47
     raiſ
    0.47
    Activations Density 0.113%

    No Known Activations