© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5005
    Prev
    Next
    INDEX
    Explanations

    words related to sports teams and the idea of being "former".

    oai_token-act-pair · gemini-2.0-flash

    football positions

    np_token-act-pair-logits · gpt-4o-mini

    sports team positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     CreateTagHelper
    -0.68
    ArgsConstructor
    -0.60
    ruptedException
    -0.57
     AssemblyCulture
    -0.56
    setVerticalGroup
    -0.55
     AssemblyProduct
    -0.52
    itron
    -0.47
    WEBPACK
    -0.47
     @"/
    -0.46
    GroupName
    -0.46
    POSITIVE LOGITS
     midfielder
    0.64
     goalkeeper
    0.60
     utility
    0.59
    keeper
    0.59
     olympique
    0.57
     midfield
    0.57
     player
    0.57
     keeper
    0.56
     defender
    0.55
    rrggbb
    0.55
    Activations Density 0.325%

    No Known Activations