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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9042
    Prev
    Next
    INDEX
    Explanations

    the word "going," sometimes near words related to purpose or goals

    oai_token-act-pair · gemini-2.0-flash

    going

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     going
    -2.42
    Going
    -2.22
     Going
    -2.17
    going
    -2.00
     GOING
    -1.98
    <bos>
    -1.73
     goin
    -1.66
    GOING
    -1.59
     goes
    -1.26
     went
    -1.23
    POSITIVE LOGITS
    GraphicsUnit
    0.66
     mxArray
    0.66
    TintMode
    0.64
     TextAppearance
    0.64
    rrggbb
    0.63
     nakalista
    0.63
    JspWriter
    0.63
    MessageOf
    0.63
    ⓧ
    0.61
    ⎨
    0.61
    Activations Density 1.915%

    No Known Activations