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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14574
    Prev
    Next
    INDEX
    Explanations

    phrases related to hitting something or someone

    oai_token-act-pair · gemini-2.0-flash

    beat

    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
     beat
    -2.80
     beats
    -2.33
    beat
    -2.33
     Beat
    -2.22
     beating
    -2.22
    Beat
    -2.19
     BEAT
    -2.05
     beaten
    -2.03
    beats
    -1.91
    Beats
    -1.73
    POSITIVE LOGITS
    WithIOException
    0.61
    AndEndTag
    0.58
    WebElementEntity
    0.56
    expandindo
    0.56
    sizeCache
    0.55
    EndContext
    0.55
    mentaux
    0.54
    MigrationBuilder
    0.53
     gql
    0.52
     <=",
    0.52
    Activations Density 4.976%

    No Known Activations