© 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. 4469
    Prev
    Next
    INDEX
    Explanations

    words, symbols, and markup related to code, databases, and queries

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "record"

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

    record/records

    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
    hilt
    -0.44
     k
    -0.42
     élector
    -0.40
    hil
    -0.40
    alk
    -0.38
    imshow
    -0.38
    енча
    -0.38
    PIT
    -0.36
    MAN
    -0.35
     suel
    -0.35
    POSITIVE LOGITS
     record
    2.22
     records
    2.00
     Record
    1.94
    record
    1.94
    Record
    1.83
    records
    1.77
     Records
    1.74
     RECORD
    1.73
    Records
    1.69
     RECORDS
    1.66
    Activations Density 3.841%

    No Known Activations