© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7992
    Prev
    Next
    INDEX
    Explanations

    terminology and language patterns used specifically in scientific or medical research papers.

    oai_token-act-pair · gemini-2.0-flash

    scientific research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    mtr
    -0.54
    ToLeft
    -0.51
    ELTS
    -0.48
    PyExc
    -0.48
     ushered
    -0.47
    hamn
    -0.47
    krishnan
    -0.46
    jface
    -0.45
    kaper
    -0.45
     Introduced
    -0.45
    POSITIVE LOGITS
    MigrationBuilder
    0.76
    getItemId
    0.64
    RefNanny
    0.60
     InkWell
    0.60
     متعلقه
    0.60
    évaluateur
    0.59
    IUrlHelper
    0.59
    setVerticalGroup
    0.58
    ItemLayout
    0.56
     виправивши
    0.55
    Activations Density 2.884%

    No Known Activations