© 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. 9971
    Prev
    Next
    INDEX
    Explanations

    the phrase "going on" or "'s going on".

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "going"

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

    going

    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
    <eos>
    -0.57
    .
    -0.53
     original
    -0.51
    ↵↵
    -0.50
     nem
    -0.49
     
    -0.49
    []
    -0.47
    ↵
    -0.47
     inter
    -0.47
     about
    -0.46
    POSITIVE LOGITS
    WithIOException
    1.15
     itſelf
    1.13
     myſelf
    1.12
     Monfieur
    1.09
     Efq
    1.02
     becauſe
    1.01
     iſt
    1.01
     ſever
    1.00
     Jefus
    0.99
     Majefty
    0.99
    Activations Density 0.142%

    No Known Activations