© 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. 14839
    Prev
    Next
    INDEX
    Explanations

    the word "research" and words associated with it

    oai_token-act-pair · gemini-2.0-flash

    terms related to research

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

    research

    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
    VideoCapture
    -0.52
    adpleegd
    -0.45
    Research
    -0.42
     ویکی‌پدیا
    -0.42
    feinander
    -0.42
     mitä
    -0.42
    AsUp
    -0.41
     RESEARCH
    -0.40
    WTA
    -0.40
     Research
    -0.40
    POSITIVE LOGITS
     EconPapers
    0.74
    RenderAtEndOf
    0.69
     InputDecoration
    0.65
    ScopeManager
    0.62
     насељу
    0.56
     onCreateView
    0.55
     effort
    0.55
     LCCN
    0.54
     Ofen
    0.54
    sstelle
    0.54
    Activations Density 1.750%

    No Known Activations