© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10293
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with the movement and tracking of objects or animals

    oai_token-act-pair · gemini-2.0-flash

    variants of the word "track"

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

    Tracking

    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
    ]")]
    -0.81
     myſelf
    -0.67
     pleaſure
    -0.66
     Houſe
    -0.65
     Theſe
    -0.64
     ſche
    -0.64
    kloped
    -0.63
     Monfieur
    -0.62
     ſeveral
    -0.62
     houſe
    -0.61
    POSITIVE LOGITS
     tracking
    1.07
     tracked
    0.96
     Tracking
    0.94
     TRACK
    0.93
     track
    0.90
     tracker
    0.89
     Track
    0.87
    tracking
    0.85
    track
    0.83
     trackers
    0.83
    Activations Density 1.521%

    No Known Activations