© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14262
    Prev
    Next
    INDEX
    Explanations

    words related to locations in Hamburg and Rotterdam, as well as some words ending in "er" and "se"

    oai_token-act-pair · gemini-2.0-flash

    Hamburg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     виправивши
    -1.13
    ViewImports
    -0.75
    AccessorTable
    -0.74
    +#+#
    -0.74
    PropertyChanging
    -0.72
    msgTypes
    -0.67
    AutoField
    -0.66
     StatefulWidget
    -0.66
    :]:
    -0.66
     оригіналу
    -0.65
    POSITIVE LOGITS
     legal
    0.52
     But
    0.50
     Italijanski
    0.46
    gente
    0.45
    TypedDataSet
    0.45
     Then
    0.44
    thral
    0.44
     legais
    0.43
    itoriale
    0.43
     .
    0.42
    Activations Density 0.534%

    No Known Activations