© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6411
    Prev
    Next
    INDEX
    Explanations

    words related to finding and taking things

    oai_token-act-pair · gemini-2.0-flash

    unique identifiers or terms related to programming or technical content

    np_token-act-pair-logits · gpt-4o-mini

    mixed excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    럴
    -0.52
     Sech
    -0.50
    につ
    -0.50
    pherals
    -0.50
    essa
    -0.49
    NOTE
    -0.49
    örer
    -0.49
     Kleine
    -0.49
     vệ
    -0.49
    quent
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.92
    ंदीखरीदारी
    0.75
     kasarigan
    0.71
     oprot
    0.70
    ValueStyle
    0.69
    setVerticalGroup
    0.68
     autorytatywna
    0.67
    contentLoaded
    0.67
     ligiloj
    0.66
    Дереккөздер
    0.66
    Activations Density 4.819%

    No Known Activations