© 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. 5293
    Prev
    Next
    INDEX
    Explanations

    small quantities described with words that often include the preposition "for"

    oai_token-act-pair · gemini-2.0-flash

    time-related terms

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

    mentions minutes, seconds

    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
     '\\;'
    -0.65
    ViewFeatures
    -0.60
    $_['
    -0.60
    IndentedString
    -0.59
    ViewImports
    -0.55
     betweenstory
    -0.55
    AspNet
    -0.51
    kháu
    -0.50
     GenerationType
    -0.48
     AttributeSet
    -0.48
    POSITIVE LOGITS
     minutes
    2.20
     minute
    2.09
    minute
    1.88
     Minutes
    1.80
    minutes
    1.72
     seconds
    1.70
     Minute
    1.70
    Minute
    1.66
     min
    1.66
    Minutes
    1.66
    Activations Density 3.525%

    No Known Activations