© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6024
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" or the helping verb "going" accompanied by other words.

    oai_token-act-pair · gemini-2.0-flash

    Before action words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     for
    -0.77
     N
    -0.55
    for
    -0.52
     All
    -0.52
     For
    -0.52
     I
    -0.52
     B
    -0.52
     (
    -0.50
    <eos>
    -0.50
     first
    -0.50
    POSITIVE LOGITS
     resourceCulture
    1.34
     nakalista
    0.98
    aarrggbb
    0.88
     myſelf
    0.86
     purpoſe
    0.86
     विश्वसनीयता
    0.84
     للمعارف
    0.84
     Majefty
    0.81
    ^(@)
    0.81
     '\\;'
    0.81
    Activations Density 1.271%

    No Known Activations