© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5749
    Prev
    Next
    INDEX
    Explanations

    mentions of an organization or person holding multiple positions or memberships in official groups

    oai_token-act-pair · gemini-2.0-flash

    Organizations and institutions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    RemoteException
    -0.72
    orologio
    -0.66
    EndContext
    -0.65
     convertView
    -0.64
    ValueGenerated
    -0.64
     gostaria
    -0.63
    ."]
    -0.63
     оригіналу
    -0.62
     estekak
    -0.62
     photolibrary
    -0.62
    POSITIVE LOGITS
     State
    0.49
    出版年
    0.48
     Defense
    0.44
    jai
    0.43
     state
    0.41
     University
    0.40
     Falls
    0.39
     paie
    0.39
     lenker
    0.38
     Board
    0.38
    Activations Density 4.084%

    No Known Activations