© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14086
    Prev
    Next
    INDEX
    Explanations

    the word "intervention" and words related to it such as "interventions"

    oai_token-act-pair · gemini-2.0-flash

    intervention

    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
    Negative Logits
    <bos>
    -1.13
    ↵↵
    -0.70
    '
    -0.66
    s
    -0.59
     mukaan
    -0.57
    ↵
    -0.55
    ‘
    -0.52
     dõi
    -0.50
     mukana
    -0.50
    {
    -0.49
    POSITIVE LOGITS
     kasarigan
    0.77
    mybatisplus
    0.77
    complexContent
    0.72
    $.}
    0.71
    ElementException
    0.71
    Composable
    0.70
    Chham
    0.68
    RTEE
    0.67
    spesies
    0.67
    IGraphics
    0.67
    Activations Density 1.051%

    No Known Activations