© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11672
    Prev
    Next
    INDEX
    Explanations

    the neuron activates on a variety of different topics but is more likely to activate on financial topics and fantasy battles.

    oai_token-act-pair · gemini-2.0-flash

    comparisons and relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ConstraintMaker
    -0.84
    AutoresizingMask
    -0.70
     defaultstate
    -0.65
     للاسماء
    -0.65
     transfieras
    -0.64
    下载附件
    -0.62
    protoimpl
    -0.61
     мәкал
    -0.60
     թվական
    -0.60
    TagMode
    -0.59
    POSITIVE LOGITS
     enhancer
    0.45
    /*
    0.44
    rogens
    0.43
    ASR
    0.43
     nostalgia
    0.43
     storico
    0.43
     storica
    0.43
    ABUL
    0.42
     niitä
    0.42
     entscheiden
    0.41
    Activations Density 0.508%

    No Known Activations