© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3505
    Prev
    Next
    INDEX
    Explanations

    words related to bedding and electrical devices

    oai_token-act-pair · gemini-2.0-flash

    bed sheets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     يتيمه
    -0.70
     المعيارى
    -0.66
    SourceChecksum
    -0.60
     SearchView
    -0.59
     Tied
    -0.56
    titleMargin
    -0.54
    sizeCache
    -0.53
     manières
    -0.52
    LEncoder
    -0.52
    BeginContext
    -0.52
    POSITIVE LOGITS
     sheet
    0.85
     sheets
    0.82
     Sheet
    0.72
    Sheet
    0.69
    sheet
    0.66
     SHEET
    0.66
     Sheets
    0.64
    msgTypes
    0.63
    sheets
    0.62
    Sheets
    0.61
    Activations Density 0.905%

    No Known Activations