© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1256
    Prev
    Next
    INDEX
    Explanations

    words and phrases around the words "keep" and "track"

    oai_token-act-pair · gemini-2.0-flash

    keep

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     يتيمه
    -0.81
    ^(@)
    -0.75
    Geplaatst
    -0.73
     surla
    -0.73
     poffible
    -0.71
     autorytatywna
    -0.71
     Shakspeare
    -0.70
     تضيفلها
    -0.67
     tetrachloride
    -0.66
     Audiodateien
    -0.65
    POSITIVE LOGITS
     tracking
    1.70
     track
    1.69
     TRACK
    1.59
     Track
    1.55
     tracked
    1.51
     Tracking
    1.49
    track
    1.48
    Track
    1.45
    TRACK
    1.39
    Tracking
    1.36
    Activations Density 2.300%

    No Known Activations