© 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. 1585
    Prev
    Next
    INDEX
    Explanations

    chemical reactions, especially related to oxides, nitrates, and gas generation

    oai_token-act-pair · gemini-2.0-flash

    reaction

    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
     resourceCulture
    -0.55
     ([]
    -0.48
    GeneratedMessage
    -0.46
     nahilalakip
    -0.44
    Extend
    -0.43
    DataSnapshot
    -0.43
    extend
    -0.42
     appelez
    -0.42
    締切
    -0.42
     createState
    -0.42
    POSITIVE LOGITS
     AssemblyVersion
    0.73
    PerformLayout
    0.68
    __':
    0.65
    <!--[
    0.63
    smithy
    0.62
    ulario
    0.60
    ENSIS
    0.58
     bezeichneter
    0.57
    rillation
    0.57
    stdc
    0.56
    Activations Density 0.752%

    No Known Activations