© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13656
    Prev
    Next
    INDEX
    Explanations

    words related to chemical processes and material science, with a focus on formal descriptions

    oai_token-act-pair · gemini-2.0-flash

    Chemical/industrial powders and processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     lapangan
    -0.57
     beban
    -0.54
     vérit
    -0.52
     helyzet
    -0.52
     tillbaka
    -0.52
     medlemmer
    -0.50
     générations
    -0.48
     répondu
    -0.48
     fleste
    -0.48
     igång
    -0.48
    POSITIVE LOGITS
    TagHelper
    0.78
    AutoScaleMode
    0.65
    oneofs
    0.63
    LookAnd
    0.62
     Akismet
    0.60
    CppMethod
    0.59
    webElementXpaths
    0.58
    IsContent
    0.58
     jadx
    0.57
    GroupLayout
    0.57
    Activations Density 34.599%

    No Known Activations