© 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. 2699
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to events, performances and exercise

    oai_token-act-pair · 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
    mic
    -0.42
    enumi
    -0.41
    Mic
    -0.39
     Neutron
    -0.38
     cứng
    -0.38
    null
    -0.35
    Neutron
    -0.35
     Mic
    -0.34
     vald
    -0.34
     ty
    -0.33
    POSITIVE LOGITS
    ReusableCell
    0.76
     crossorigin
    0.73
    WebVitals
    0.73
    awtextra
    0.72
     OFDb
    0.71
     AssemblyCulture
    0.70
    HtmlAttribute
    0.70
    帖最后由
    0.69
     ProtoMessage
    0.68
    styleType
    0.68
    Activations Density 1.662%

    No Known Activations