© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 32
    Prev
    Next
    INDEX
    Explanations

    the word "do" or "Do"

    oai_token-act-pair · gemini-2.0-flash

    do

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    MessageTagHelper
    -0.58
    do
    -0.54
    MLLoader
    -0.54
    )");
    -0.50
     AssemblyCulture
    -0.49
    Rhestr
    -0.48
    felt
    -0.47
    atrician
    -0.44
    ✨:
    -0.44
    ########.
    -0.44
    POSITIVE LOGITS
    ONS
    0.54
    VES
    0.54
    Composable
    0.52
    cessions
    0.50
    INER
    0.50
    ves
    0.50
    ons
    0.50
    IGH
    0.49
    LLER
    0.48
    REDIT
    0.47
    Activations Density 4.276%

    No Known Activations