© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 14976
    Prev
    Next
    INDEX
    Explanations

    words related to people and seeing.

    oai_token-act-pair · gemini-2.0-flash

    people

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     đã
    -0.49
    版
    -0.46
    recht
    -0.44
     verdade
    -0.44
    zyst
    -0.43
    losse
    -0.43
     telah
    -0.41
    SLOT
    -0.39
    CORE
    -0.38
    TextBoxColumn
    -0.38
    POSITIVE LOGITS
    yntaxException
    0.90
    PropertyChanging
    0.69
    SequentialGroup
    0.66
    Искәрмәләр
    0.63
    CompleteListener
    0.62
     Administrativna
    0.60
    Jereo
    0.60
    InsertCommand
    0.60
    tanleria
    0.59
     nahilalakip
    0.59
    Activations Density 4.981%

    No Known Activations