© 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. 3662
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to domestic and personal care tasks

    oai_token-act-pair · 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
    RenderAtEndOf
    -0.61
    NewUrlParser
    -0.53
    قایناقلار
    -0.50
     getCode
    -0.49
    ingang
    -0.49
     SIMBAD
    -0.48
    ogia
    -0.48
     définiti
    -0.48
     للاسماء
    -0.48
    beginTransaction
    -0.47
    POSITIVE LOGITS
     nonatomic
    0.55
    KeySpec
    0.55
    ypress
    0.50
    gartner
    0.50
    GINIA
    0.50
    ciss
    0.50
     MainAxisSize
    0.49
    PathParam
    0.48
    MessageState
    0.47
     CURIAM
    0.47
    Activations Density 1.365%

    No Known Activations