© 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. 11474
    Prev
    Next
    INDEX
    Explanations

    words or phrases that describe processes, conditions, or qualities that are difficult or extreme

    oai_token-act-pair · gemini-2.0-flash

    Qualities

    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
     &___
    -0.75
     ModelExpression
    -0.72
     ExecuteAsync
    -0.70
     Administrativna
    -0.68
     pinulongan
    -0.67
    MessageTagHelper
    -0.66
    twimg
    -0.66
    WriteBarrier
    -0.65
    RTLR
    -0.64
    atguigu
    -0.64
    POSITIVE LOGITS
     ’
    0.48
     rowspan
    0.47
    ましい
    0.42
     zucchero
    0.42
     `
    0.40
    objPHPExcel
    0.40
     God
    0.40
     style
    0.39
     نے
    0.39
     ses
    0.39
    Activations Density 1.108%

    No Known Activations