© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7088
    Prev
    Next
    INDEX
    Explanations

    a time of when something happened, and references about food.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "age"

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

    age

    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
    SourceChecksum
    -0.84
    ValueStyle
    -0.69
    Tikang
    -0.64
    出版年
    -0.63
    TagMode
    -0.63
    ErrUnexpectedEOF
    -0.63
    WebElementEntity
    -0.63
    PerformLayout
    -0.60
     BoxFit
    -0.60
    談社
    -0.59
    POSITIVE LOGITS
     aging
    0.90
     ageing
    0.84
     age
    0.78
    aging
    0.70
    Age
    0.69
     ages
    0.69
     aged
    0.69
     Age
    0.68
     Aging
    0.66
    age
    0.63
    Activations Density 1.936%

    No Known Activations