© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15847
    Prev
    Next
    INDEX
    Explanations

    JSON-like data structures, particularly those with bracketed lists and nested objects, possibly related to date/time formats or UI elements

    oai_token-act-pair · gemini-2.0-flash

    code/data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    enterOuterAlt
    -0.61
    ⓘ
    -0.50
    Hochspringen
    -0.50
    setWindow
    -0.50
     appended
    -0.46
    <bos>
    -0.46
    存于互联网档案馆
    -0.46
     Maharaja
    -0.45
     setLoading
    -0.44
     same
    -0.44
    POSITIVE LOGITS
    ManagedBean
    0.62
    下一篇
    0.60
     EconPapers
    0.59
    SEGUIR
    0.58
    homonymie
    0.57
     kasarigan
    0.54
    Ỉ
    0.53
     تضيفلها
    0.52
    mær
    0.52
    TestingModule
    0.51
    Activations Density 17.685%

    No Known Activations