© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13344
    Prev
    Next
    INDEX
    Explanations

    words associated with conclusions or statements in academic papers

    oai_token-act-pair · gemini-2.0-flash

    academic analysis

    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
     culturelles
    -0.63
     médicaux
    -0.61
     supérieures
    -0.59
     étrangères
    -0.58
     scolaires
    -0.57
     judiciales
    -0.56
     sauvages
    -0.55
     policiales
    -0.55
     militaires
    -0.54
     alimentaires
    -0.54
    POSITIVE LOGITS
     resourceCulture
    0.72
    ScopeManager
    0.69
     gynhyrchwyd
    0.66
     esternos
    0.63
     skak
    0.63
     ExecuteAsync
    0.61
    #
    0.57
    manship
    0.56
    accumulative
    0.55
    openzeppelin
    0.54
    Activations Density 0.542%

    No Known Activations