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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8151
    Prev
    Next
    INDEX
    Explanations

    mentions of driving in a car

    oai_token-act-pair · gemini-2.0-flash

    variations of the verb 'drive'

    np_token-act-pair-logits · gpt-4o-mini

    drive/driving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     walk
    -1.65
    walk
    -1.63
     Walk
    -1.58
    Walk
    -1.55
     walking
    -1.45
     WALK
    -1.43
     walked
    -1.41
    WALK
    -1.41
    walking
    -1.39
     walks
    -1.38
    POSITIVE LOGITS
     drives
    0.80
     drive
    0.71
     Drives
    0.70
     driving
    0.68
    Driving
    0.66
    drives
    0.66
    drive
    0.63
    driving
    0.63
     drove
    0.60
     roulant
    0.60
    Activations Density 2.401%

    No Known Activations