© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6776
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "too" and, to a much lesser extent, "hopefully"

    oai_token-act-pair · gemini-2.0-flash

    too

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    initialise
    -0.88
    alised
    -0.76
     onwards
    -0.74
    labour
    -0.73
    behaviour
    -0.73
     colourful
    -0.73
     realisation
    -0.70
     generalised
    -0.70
     mobilisation
    -0.69
     fuelled
    -0.69
    POSITIVE LOGITS
    setVerticalGroup
    0.73
    GEBURTSDATUM
    0.71
    millimeters
    0.71
     Afterward
    0.71
    FormTagHelper
    0.70
     &___
    0.66
     remodeling
    0.65
    :✨
    0.65
     Remodeling
    0.65
    CGRectMake
    0.64
    Activations Density 0.353%

    No Known Activations