© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 804
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with locations, especially the UK and England, Queen Victoria, and healthcare.

    oai_token-act-pair · gemini-2.0-flash

    broad concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    glTranslatef
    -0.52
    utscher
    -0.45
     Blatt
    -0.45
     Antara
    -0.44
    UrlResolution
    -0.44
    espé
    -0.43
    opsida
    -0.43
    trex
    -0.43
     Ostat
    -0.42
     vectors
    -0.42
    POSITIVE LOGITS
    addCriterion
    0.72
     idéia
    0.71
     تضيفلها
    0.68
    AccessorTable
    0.67
    
    0.66
     sauvages
    0.65
    StoryboardSegue
    0.65
     concernés
    0.65
     avoient
    0.63
    FunctionFlags
    0.63
    Activations Density 6.331%

    No Known Activations