© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2514
    Prev
    Next
    INDEX
    Explanations

    acronyms and phrases relating to stages of life, tournaments, materials, devices, and technical terms

    oai_token-act-pair · gemini-2.0-flash

    technical prose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     sw
    -0.48
    حوالہ
    -0.48
    lň
    -0.47
    cessive
    -0.46
     My
    -0.45
    ropia
    -0.43
    appé
    -0.42
    ঔ
    -0.42
     Italijanski
    -0.42
     Gegen
    -0.42
    POSITIVE LOGITS
    +#+#
    0.89
     Normdatei
    0.75
    ContentAsync
    0.69
     jScrollPane
    0.67
    脚注の使い方
    0.67
     Constitucional
    0.64
     AssemblyCulture
    0.62
     SIAM
    0.61
    Rohy
    0.61
    SPATH
    0.61
    Activations Density 1.436%

    No Known Activations