© 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. 11539
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of inventions

    oai_token-act-pair · gemini-2.0-flash

    Containment or storage

    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
     shingle
    -0.55
     parapet
    -0.54
    onymes
    -0.52
     Permalink
    -0.50
    Prompt
    -0.48
    phos
    -0.48
    chooser
    -0.47
    жели
    -0.46
    ereum
    -0.46
    nola
    -0.46
    POSITIVE LOGITS
    Rohy
    0.69
    +#+#
    0.68
    iNdEx
    0.65
    InputBorder
    0.65
    twimg
    0.63
     ligiloj
    0.62
    Хьажоргаш
    0.59
    oredCriteria
    0.59
    ViewInit
    0.56
    migrationBuilder
    0.55
    Activations Density 0.669%

    No Known Activations