© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6884
    Prev
    Next
    INDEX
    Explanations

    words or short phrases commonly used in online chat, especially in the context of technical support and discussion.

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    foreign questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     يتيمه
    -0.93
    +#+
    -0.78
    RegistryLite
    -0.73
     &___
    -0.67
    BeginContext
    -0.66
     تضيفلها
    -0.61
    DrawerToggle
    -0.61
    MessageTagHelper
    -0.57
     समीक्षाओं
    -0.56
     esternos
    -0.56
    POSITIVE LOGITS
    gantian
    0.51
     Sheet
    0.48
    DOCTYPE
    0.48
    은
    0.45
     ExecuteAsync
    0.45
     Eis
    0.44
     han
    0.43
    bebasan
    0.43
     je
    0.43
     SHEET
    0.43
    Activations Density 1.104%

    No Known Activations