© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4109
    Prev
    Next
    INDEX
    Explanations

    words related to cooking, temperature, and measurements

    oai_token-act-pair · gemini-2.0-flash

    temperature

    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
    AutoScaleMode
    -0.94
     NSCoder
    -0.76
     дописавши
    -0.72
     CreateTagHelper
    -0.71
    ędzie
    -0.70
     ExecuteAsync
    -0.68
     تانيه
    -0.67
     resolution
    -0.61
     resolutions
    -0.60
    脚注の使い方
    -0.59
    POSITIVE LOGITS
    stande
    0.52
    зулта
    0.51
     Outlet
    0.47
    orp
    0.47
    剪
    0.46
    Team
    0.46
     Latimer
    0.45
     penser
    0.44
    udio
    0.43
     Team
    0.43
    Activations Density 2.161%

    No Known Activations