© 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. 13346
    Prev
    Next
    INDEX
    Explanations

    words and phrases with multiple meanings or words in different languages

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "current"

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

    current

    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
    CGRectMake
    -0.43
    انيف
    -0.43
    lüğü
    -0.43
    RRect
    -0.43
    richTextPanel
    -0.42
    évaluateur
    -0.41
     parseFrom
    -0.41
     dø
    -0.40
    ादी
    -0.40
    ctez
    -0.38
    POSITIVE LOGITS
     current
    2.83
    current
    2.56
     CURRENT
    2.53
     currently
    2.47
     Current
    2.45
    Current
    2.44
    CURRENT
    2.30
     presently
    2.28
    currently
    2.23
     Currently
    2.14
    Activations Density 0.804%

    No Known Activations