© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6363
    Prev
    Next
    INDEX
    Explanations

    verbs related to performing an action

    oai_token-act-pair · gemini-2.0-flash

    activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     CanadaChoose
    -0.78
     EconPapers
    -0.73
    Jeografia
    -0.62
    Autoritní
    -0.59
     tartalomajánló
    -0.57
    AddField
    -0.57
    Портал
    -0.56
    省市镇
    -0.56
    astéroïdes
    -0.56
     ویکی‌پدی
    -0.54
    POSITIVE LOGITS
    ={({
    0.66
     realise
    0.65
     analysed
    0.63
     programmes
    0.62
     Programme
    0.62
     recognise
    0.60
     analyse
    0.58
     analysing
    0.58
     learnt
    0.57
     Programmes
    0.57
    Activations Density 1.341%

    No Known Activations