© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8707
    Prev
    Next
    INDEX
    Explanations

    words ending in "ed" or "use" and related to emotional states, words related to fuses, and the words "fused" and "une".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    webdriver
    -0.59
    LoadScene
    -0.58
    الإنجليزية
    -0.56
    XmlAttribute
    -0.54
     surla
    -0.54
    clientHeight
    -0.53
     schließen
    -0.51
     tygod
    -0.50
     closed
    -0.50
    AccessorTable
    -0.48
    POSITIVE LOGITS
    новниш
    0.65
    Nhưng
    0.59
    égias
    0.59
    +#+#
    0.58
    fattning
    0.57
    OMBIA
    0.57
    дото
    0.57
    GEBURTSDATUM
    0.55
    odeficiency
    0.54
     AssemblyCulture
    0.54
    Activations Density 1.010%

    No Known Activations