© 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. 7257
    Prev
    Next
    INDEX
    Explanations

    years mentioned within sentences, particularly those in the mid-20th century, and also seems to activate on related context like opera houses and locations.

    oai_token-act-pair · gemini-2.0-flash

    technical mixed language

    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
    AutoScaleMode
    -0.66
    numerusform
    -0.61
     оригіналу
    -0.55
    abestanden
    -0.54
     AssemblyCompany
    -0.54
    expandindo
    -0.54
     sumpay
    -0.53
    BeginContext
    -0.50
    ngOn
    -0.50
    PyExc
    -0.50
    POSITIVE LOGITS
    UserScript
    0.68
    onViewCreated
    0.60
     siebie
    0.57
     prochaines
    0.54
    ECS
    0.54
    quelize
    0.54
    lue
    0.50
    ogener
    0.48
    SuccessListener
    0.48
     sequelize
    0.47
    Activations Density 10.835%

    No Known Activations