© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4281
    Prev
    Next
    INDEX
    Explanations

    words associated with streets, roads, and pedestrian activity

    oai_token-act-pair · gemini-2.0-flash

    pedestrian areas/paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     مشين
    -0.57
    ंदीखरीदारी
    -0.57
    verifyException
    -0.51
     paillettes
    -0.49
     odeur
    -0.49
     modernes
    -0.48
     Sly
    -0.48
     industriales
    -0.47
     complètes
    -0.47
     perdere
    -0.47
    POSITIVE LOGITS
     pedestrians
    0.76
     متعلقه
    0.71
     walkers
    0.71
     foot
    0.71
    estrian
    0.70
     walk
    0.69
    步行
    0.68
    🚶
    0.66
     walking
    0.66
     pedestrian
    0.66
    Activations Density 0.750%

    No Known Activations