© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6038
    Prev
    Next
    INDEX
    Explanations

    the word "draft."

    oai_token-act-pair · gemini-2.0-flash

    draft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Ce
    -0.62
     Qu
    -0.61
    atru
    -0.59
     sot
    -0.59
     Ap
    -0.57
     Ir
    -0.57
     ket
    -0.56
     Pu
    -0.56
     Mit
    -0.56
    andır
    -0.54
    POSITIVE LOGITS
     Económica
    0.88
    httphttps
    0.85
     المعيارى
    0.85
     mijne
    0.84
     HFILL
    0.77
     Constitucional
    0.77
    adeloupe
    0.76
     zijne
    0.76
     adelante
    0.75
    berdayakan
    0.75
    Activations Density 0.747%

    No Known Activations