© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    numerical data, including numbers, percentages, and versions, possibly within tables or code.

    oai_token-act-pair · gemini-2.0-flash

    Code and data tables

    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
     примеру
    -0.48
    VisualStudio
    -0.43
     ioutil
    -0.41
    jukan
    -0.40
    NamedQuery
    -0.40
    =").
    -0.40
    mbre
    -0.40
    =")
    -0.39
    EndContext
    -0.39
    MethodManager
    -0.38
    POSITIVE LOGITS
     resourceCulture
    0.96
    itinéraire
    0.77
    Personendaten
    0.75
    Източници
    0.74
    niająca
    0.65
    __(/*!
    0.65
    xase
    0.64
    ActionMode
    0.63
     Italijanski
    0.63
    IUrlHelper
    0.62
    Activations Density 1.310%

    No Known Activations