© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7613
    Prev
    Next
    INDEX
    Explanations

    the word "for" preceded and followed by numbers or words indicating quantity or time

    oai_token-act-pair · gemini-2.0-flash

    for/in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     years
    -1.22
     months
    -1.15
     awhile
    -1.13
     longest
    -1.10
     long
    -1.10
     YEARS
    -1.09
    Years
    -1.08
    years
    -1.08
    months
    -1.06
     Years
    -1.01
    POSITIVE LOGITS
    PHPExcel
    0.50
    ásban
    0.48
    ônico
    0.43
    ../../../
    0.43
    Demografie
    0.40
     Coward
    0.40
     Lesnar
    0.40
    ance
    0.40
    noopener
    0.40
    ../
    0.39
    Activations Density 0.467%

    No Known Activations