© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16020
    Prev
    Next
    INDEX
    Explanations

    language related to study participants taking part and consenting to studies

    oai_token-act-pair · gemini-2.0-flash

    participation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     NSCoder
    -0.66
     BoxFit
    -0.61
    出版年
    -0.59
    LookAnd
    -0.58
    Soorten
    -0.57
    rungsseite
    -0.57
     newBuilder
    -0.56
    awtextra
    -0.56
     ویکی‌پدیا
    -0.56
     SwitchCompat
    -0.54
    POSITIVE LOGITS
     participation
    2.14
     participate
    2.03
     participating
    1.98
     Participation
    1.95
    particip
    1.92
     participates
    1.89
     participated
    1.88
     PARTICIP
    1.88
    Participation
    1.83
    Participating
    1.79
    Activations Density 1.975%

    No Known Activations