© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10022
    Prev
    Next
    INDEX
    Explanations

    common words indicating a topic of research or study

    oai_token-act-pair · gemini-2.0-flash

    Notes

    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
     Formations
    -0.92
    Designs
    -0.82
     Volumes
    -0.81
     Sizes
    -0.79
     Populations
    -0.78
     Forms
    -0.78
     Releases
    -0.78
     Phases
    -0.77
     Installations
    -0.77
     Formats
    -0.76
    POSITIVE LOGITS
     Notes
    0.66
    Notes
    0.63
     Comments
    0.60
     Hints
    0.57
    Key
    0.56
     NOTES
    0.56
    Comments
    0.55
     Keys
    0.53
     Questions
    0.53
    Keys
    0.52
    Activations Density 7.686%

    No Known Activations