© 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. 6432
    Prev
    Next
    INDEX
    Explanations

    capitalized words and descriptive titles

    oai_token-act-pair · gemini-2.0-flash

    Professions

    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
     Direction
    -0.93
     Availability
    -0.78
     Purpose
    -0.76
     Opportunity
    -0.76
     Progress
    -0.76
     Access
    -0.75
     Explanation
    -0.74
     Responsibility
    -0.73
     Basis
    -0.71
     Presence
    -0.71
    POSITIVE LOGITS
     Film
    0.70
     Scientists
    0.69
     Newspaper
    0.68
     Newspapers
    0.65
     Farmers
    0.65
     Companies
    0.65
     Journalists
    0.64
    Film
    0.63
     Journalist
    0.63
     Lawyer
    0.62
    Activations Density 8.537%

    No Known Activations