© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10446
    Prev
    Next
    INDEX
    Explanations

    words related to groups of fans and people who come together at events

    oai_token-act-pair · gemini-2.0-flash

    terms related to gathering

    np_token-act-pair-logits · gpt-4o-mini

    gathering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    IntoConstraints
    -0.69
     eventdata
    -0.67
    findpost
    -0.66
     Beſ
    -0.63
     étoient
    -0.60
     ſeveral
    -0.58
     myſelf
    -0.57
     Theſe
    -0.57
     Monfieur
    -0.57
     becauſe
    -0.54
    POSITIVE LOGITS
     gather
    0.82
     gathered
    0.78
     gathers
    0.66
    gather
    0.64
     line
    0.61
     Line
    0.60
    Line
    0.58
     gathering
    0.57
     flock
    0.57
     Gather
    0.55
    Activations Density 1.985%

    No Known Activations