© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2989
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to describing something in terms of another language, especially literally

    oai_token-act-pair · gemini-2.0-flash

    translation/meaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     magnetization
    -0.47
     Dray
    -0.45
     hyal
    -0.45
     mammals
    -0.45
     edn
    -0.45
     XNUMX
    -0.45
     emend
    -0.45
     Etr
    -0.45
     Antar
    -0.44
    nemia
    -0.44
    POSITIVE LOGITS
     يتيمه
    0.69
    $_['
    0.68
    PyExc
    0.67
    تقاوى
    0.67
     esternos
    0.66
    :✨
    0.63
    Personendaten
    0.60
    UnusedPrivate
    0.59
     AssemblyProduct
    0.58
    KommentareTeilen
    0.58
    Activations Density 0.568%

    No Known Activations