© 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. 4620
    Prev
    Next
    INDEX
    Explanations

    mentions of military deployments including specific dates, locations, and units

    oai_token-act-pair · gemini-2.0-flash

    depression and/or deployment

    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
     deploy
    -2.33
     deployment
    -2.23
     deployed
    -2.22
     Deploy
    -2.17
     Deployment
    -2.11
     deploying
    -2.11
    Deploy
    -2.05
    deploy
    -1.96
     deployments
    -1.91
    deployment
    -1.89
    POSITIVE LOGITS
     autorytatywna
    0.62
    NavItem
    0.52
     uncut
    0.48
    ynchrotron
    0.47
    וויק
    0.47
    Viki
    0.47
     Osm
    0.46
     auroit
    0.46
     Ause
    0.46
    osm
    0.45
    Activations Density 1.882%

    No Known Activations