© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4839
    Prev
    Next
    INDEX
    Explanations

    the word "heart" and words related to time, specifically "time" itself or other related words like "period," "era," and "agenda"

    oai_token-act-pair · gemini-2.0-flash

    heart

    np_max-act · gemini-2.0-flash

    heart

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     idéia
    -0.68
     feront
    -0.54
     automatiques
    -0.54
     einzu
    -0.54
    ibatis
    -0.52
     noël
    -0.50
    IBar
    -0.49
     semblables
    -0.49
    ModelSerializer
    -0.49
    qü
    -0.48
    POSITIVE LOGITS
     CURIAM
    0.86
    脚注の使い方
    0.82
    abestanden
    0.70
    ArgumentParser
    0.69
    WithIOException
    0.68
     Савезне
    0.67
    {}{}
    0.66
    󠁿
    0.64
     neighbour
    0.64
    ArrowToggle
    0.64
    Activations Density 0.304%

    No Known Activations