© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11094
    Prev
    Next
    INDEX
    Explanations

    references to islands, kingdoms, or geographical entities, with a particular emphasis on Greece and Denmark.

    oai_token-act-pair · gemini-2.0-flash

    place names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     autorytatywna
    -0.70
     BoxFit
    -0.68
    tvguidetime
    -0.59
    IntoConstraints
    -0.58
     lenker
    -0.57
    awaiter
    -0.55
    ValueStyle
    -0.54
    pexpr
    -0.54
    withIdentifier
    -0.52
    DateTimeField
    -0.50
    POSITIVE LOGITS
    ceira
    0.57
     Rhodes
    0.53
     Guernsey
    0.52
     BrowserModule
    0.52
    出版年
    0.51
     Mallorca
    0.50
     Nantucket
    0.50
    Skye
    0.48
    loroethene
    0.48
    Bromoform
    0.47
    Activations Density 1.020%

    No Known Activations