© 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. 4461
    Prev
    Next
    INDEX
    Explanations

    the term "this" followed by a time-related word

    oai_token-act-pair · gemini-2.0-flash

    the word 'this'

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

    this

    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
     day
    -1.61
     Day
    -1.45
    Day
    -1.41
    day
    -1.39
     DAY
    -1.34
    DAY
    -1.13
     día
    -1.02
     giorno
    -0.91
     день
    -0.75
     DÍA
    -0.75
    POSITIVE LOGITS
     winter
    0.68
     weeks
    0.63
     WaitForSeconds
    0.63
     summer
    0.60
     evenings
    0.60
     past
    0.60
    URLException
    0.57
    yntaxException
    0.57
     evening
    0.54
    __*/
    0.54
    Activations Density 0.407%

    No Known Activations