© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13485
    Prev
    Next
    INDEX
    Explanations

    article references including numbers, dois, arxiv identifiers, and author names in a specific bracketed format.

    oai_token-act-pair · gemini-2.0-flash

    academic publications

    np_max-act · 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
     }}"></
    -0.63
     viewType
    -0.63
    reggio
    -0.58
    DockStyle
    -0.57
     चीज़ों
    -0.57
     سكانية
    -0.57
    ])));
    -0.56
     becauſe
    -0.56
     iconLine
    -0.55
    writeFieldEnd
    -0.54
    POSITIVE LOGITS
    غب
    0.44
    保
    0.41
    avyzd
    0.40
     genu
    0.40
    Affection
    0.39
    golang
    0.39
    磺
    0.39
     rezerv
    0.37
    apt
    0.37
    gow
    0.37
    Activations Density 0.715%

    No Known Activations