© 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. 12998
    Prev
    Next
    INDEX
    Explanations

    groups of people gathered around some object

    oai_token-act-pair · gemini-2.0-flash

    words related to gathering or assembling

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

    gather

    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
    ixas
    -0.48
     Rost
    -0.48
    брю
    -0.47
     exporting
    -0.45
    couvrez
    -0.45
     Manus
    -0.43
    bcryptjs
    -0.43
     SPDX
    -0.43
     exports
    -0.43
     Chriftian
    -0.43
    POSITIVE LOGITS
     gather
    2.09
     gathered
    2.08
     gathers
    1.94
     gathering
    1.92
     Gather
    1.80
    gathering
    1.73
    Gather
    1.72
    Gathering
    1.70
    gather
    1.66
     Gathering
    1.66
    Activations Density 3.529%

    No Known Activations