© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11544
    Prev
    Next
    INDEX
    Explanations

    words related to personal experiences involving history, location, senses, and faith

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     betweenstory
    -0.90
    UnusedPrivate
    -0.82
    parsedMessage
    -0.78
    SourceChecksum
    -0.78
     препратки
    -0.75
     mergeFrom
    -0.74
    AsUp
    -0.73
    createCanvas
    -0.73
    tagext
    -0.72
    انيف
    -0.69
    POSITIVE LOGITS
    mble
    0.49
    WebVitals
    0.49
    hir
    0.48
    الإنجليزية
    0.47
    <?
    0.47
    haj
    0.45
     depositphotos
    0.44
    cgi
    0.44
     sticking
    0.44
    atie
    0.43
    Activations Density 1.167%

    No Known Activations