© 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. 10842
    Prev
    Next
    INDEX
    Explanations

    words that suggest the topic is travel destinations, historical sites, and old landmarks

    oai_token-act-pair · gemini-2.0-flash

    terms related to building or construction

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

    building construction

    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
    Parcelize
    -0.70
    kwds
    -0.54
    FetchType
    -0.49
    rxjs
    -0.49
    iele
    -0.49
     mxArray
    -0.49
     BorderRadius
    -0.48
     mapStateToProps
    -0.47
     onCreateView
    -0.47
     cellpadding
    -0.47
    POSITIVE LOGITS
     built
    0.91
     Construction
    0.83
     constructed
    0.83
     construction
    0.82
     Built
    0.82
     builder
    0.81
    Construction
    0.81
    Built
    0.80
    built
    0.80
    construction
    0.77
    Activations Density 4.479%

    No Known Activations