© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2518
    Prev
    Next
    INDEX
    Explanations

    the word "watch" or variations of it.

    oai_token-act-pair · gemini-2.0-flash

    watch

    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
     watch
    -2.83
     Watch
    -2.56
    Watch
    -2.45
    watch
    -2.42
     WATCH
    -2.28
     watched
    -2.17
     watching
    -2.08
     watches
    -2.06
    WATCH
    -2.02
     Watching
    -1.84
    POSITIVE LOGITS
    OGND
    0.85
    InSection
    0.82
    EndContext
    0.69
     Roskov
    0.66
    PhysRev
    0.63
    BoxShadow
    0.63
     autorytatywna
    0.61
    adaptiveStyles
    0.59
     diph
    0.59
    IsContent
    0.59
    Activations Density 2.562%

    No Known Activations