© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1626
    Prev
    Next
    INDEX
    Explanations

    references to time

    oai_token-act-pair · gemini-2.0-flash

    field

    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
    ScopeManager
    -0.50
     natuurlijk
    -0.49
     opportunity
    -0.46
    strup
    -0.43
     đơn
    -0.43
    —
    -0.42
     utafitiHapana
    -0.41
    PageContext
    -0.41
     OMITBAD
    -0.41
     keting
    -0.39
    POSITIVE LOGITS
    OGND
    0.91
    Personensuche
    0.81
    ագրություններ
    0.75
     مواليد
    0.72
    SharedCtor
    0.71
    esModule
    0.68
    sizeCache
    0.68
    verifyException
    0.65
    InputBorder
    0.65
     تضيفلها
    0.65
    Activations Density 12.856%

    No Known Activations