© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1542
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to encouraging something to improve something else

    oai_token-act-pair · gemini-2.0-flash

    encouragement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.54
     Mass
    -0.51
    atri
    -0.50
     '
    -0.50
     trinh
    -0.49
     pó
    -0.49
     alun
    -0.48
    pik
    -0.47
    öm
    -0.47
     solu
    -0.47
    POSITIVE LOGITS
     '\\;'
    0.81
    Autoritní
    0.75
    StoryboardSegue
    0.69
    rungsseite
    0.67
    ToBounds
    0.63
    +#+#
    0.63
    enação
    0.62
     pinulongan
    0.62
     تضيفلها
    0.62
     Derfor
    0.61
    Activations Density 2.641%

    No Known Activations