© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3339
    Prev
    Next
    INDEX
    Explanations

    a variety of terms related to team sports, medical screenings, or something being sought or tied together

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "for"

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

    for

    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
    脚注の使い方
    -0.84
    DockStyle
    -0.82
     EconPapers
    -0.80
    Portale
    -0.78
    KommentareTeilen
    -0.77
     Administrativna
    -0.75
    ThroughAttribute
    -0.75
    aarrggbb
    -0.75
    :✨
    -0.73
    RTEE
    -0.73
    POSITIVE LOGITS
     for
    2.53
    for
    1.70
     voor
    1.30
     für
    1.27
     FOR
    1.27
     For
    1.22
     untuk
    1.22
     för
    1.16
     для
    1.13
     pentru
    1.12
    Activations Density 10.560%

    No Known Activations