© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12477
    Prev
    Next
    INDEX
    Explanations

    the word "study" and words associated with research

    oai_token-act-pair · gemini-2.0-flash

    academic studies

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

    study

    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
    はじめに
    -0.74
    MethodManager
    -0.66
    #+#
    -0.63
     Мексичка
    -0.63
    #
    -0.62
    ipun
    -0.60
     AIT
    -0.59
    icoot
    -0.58
    ArrowToggle
    -0.57
    UnitTesting
    -0.57
    POSITIVE LOGITS
    깥
    0.53
     among
    0.48
     فريبيس
    0.48
     giù
    0.47
    hab
    0.47
     buone
    0.47
     voeren
    0.46
     chiave
    0.46
    zeň
    0.46
    ěž
    0.45
    Activations Density 4.052%

    No Known Activations