© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10890
    Prev
    Next
    INDEX
    Explanations

    quotes from sports news articles

    oai_token-act-pair · gemini-2.0-flash

    News and sports articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     дописавши
    -0.88
    CodeAttribute
    -0.76
    AnchorStyles
    -0.75
     ujednoznacz
    -0.75
    ReusableCell
    -0.73
    出版年
    -0.72
     resourceCulture
    -0.71
     invokingState
    -0.71
    StoryboardSegue
    -0.70
    Geplaatst
    -0.69
    POSITIVE LOGITS
     AspNetCore
    0.44
    P
    0.44
     P
    0.38
    Drupal
    0.34
     області
    0.34
     trình
    0.33
    труд
    0.33
    p
    0.32
     S
    0.32
    PrototypeOf
    0.32
    Activations Density 0.687%

    No Known Activations