© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6788
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers, especially "first"

    oai_token-act-pair · gemini-2.0-flash

    time-related terms

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

    time or sequence

    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
    ècie
    -0.56
     vooraf
    -0.53
     first
    -0.51
     asupra
    -0.51
    first
    -0.50
    Jereo
    -0.49
    acağına
    -0.48
     ensimmä
    -0.47
    LElement
    -0.46
    ิมพ์
    -0.46
    POSITIVE LOGITS
    WebElementEntity
    0.69
     trip
    0.63
     day
    0.59
    //
    0.57
     weeks
    0.55
     month
    0.54
     intervention
    0.54
     campaign
    0.53
     week
    0.53
     days
    0.53
    Activations Density 1.289%

    No Known Activations