© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11222
    Prev
    Next
    INDEX
    Explanations

    the word "continue"

    oai_token-act-pair · gemini-2.0-flash

    continue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     continue
    -1.62
     continues
    -1.41
    continue
    -1.34
     continuing
    -1.27
     Continue
    -1.15
     continued
    -1.10
     CONTINUE
    -1.05
    continues
    -1.04
    Continuing
    -1.04
     Continuing
    -1.02
    POSITIVE LOGITS
    MigrationBuilder
    0.49
     exécu
    0.46
    ˌ
    0.45
    ฤ
    0.45
     varier
    0.44
    lig
    0.44
     masas
    0.43
    AddHtmlAttribute
    0.43
    mendation
    0.43
     múl
    0.43
    Activations Density 0.569%

    No Known Activations