© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16022
    Prev
    Next
    INDEX
    Explanations

    mentions of Australian things, locations and companies, often in association with the word "the".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    WRENCE
    -0.63
    κτηρισ
    -0.57
     pymongo
    -0.57
    mopolitan
    -0.55
    setForm
    -0.55
     TextEditing
    -0.55
    Bev
    -0.54
    pement
    -0.54
    Dermott
    -0.52
    Obrázky
    -0.51
    POSITIVE LOGITS
    日閲覧
    0.69
     noDo
    0.68
    DockStyle
    0.65
    AndEndTag
    0.63
    NameInMap
    0.56
    rungsseite
    0.54
    currentColor
    0.52
    Diwedd
    0.52
    ########.
    0.52
     ExecuteAsync
    0.52
    Activations Density 2.870%

    No Known Activations