© 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. 14218
    Prev
    Next
    INDEX
    Explanations

    names of people and sports teams, and mentions of Ireland/Britain

    oai_token-act-pair · gemini-2.0-flash

    Rugby and British places

    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
     body
    -1.66
     Body
    -1.47
    body
    -1.41
    Body
    -1.38
     BODY
    -1.27
    BODY
    -1.10
     cuerpo
    -0.87
     bodies
    -0.87
     Körper
    -0.87
    bodies
    -0.85
    POSITIVE LOGITS
    awtextra
    0.56
     phù
    0.55
    postmedia
    0.55
    webElement
    0.52
    ForRow
    0.50
    ORCID
    0.49
     convient
    0.47
    WithMany
    0.47
    Migrations
    0.46
    aimer
    0.46
    Activations Density 2.181%

    No Known Activations