© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5387
    Prev
    Next
    INDEX
    Explanations

    words that add emphasis to situations, often related to violence.

    oai_token-act-pair · gemini-2.0-flash

    actions related to jumping

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

    jumping

    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
     signs
    -0.46
    upsi
    -0.43
    mbert
    -0.43
     taus
    -0.43
     signe
    -0.42
    hanger
    -0.41
     sign
    -0.40
    Predecesor
    -0.40
    IRC
    -0.40
    ppelin
    -0.40
    POSITIVE LOGITS
     jumped
    0.79
     CreateTagHelper
    0.77
     leapt
    0.75
     leaping
    0.75
    JUMP
    0.73
    InitVars
    0.72
    jump
    0.72
     leaped
    0.71
     jump
    0.70
    DrawerToggle
    0.69
    Activations Density 1.657%

    No Known Activations