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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5545
    Prev
    Next
    INDEX
    Explanations

    tokens frequently occurring when describing art and craft projects

    oai_token-act-pair · gemini-2.0-flash

    words related to hearts and symbols

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

    shapes and symbols

    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
     незавершена
    -0.46
     Mangel
    -0.44
     viſ
    -0.44
     juſ
    -0.44
     Tark
    -0.43
     ejemplar
    -0.43
     Isu
    -0.43
     Geen
    -0.42
    tyl
    -0.42
    ressible
    -0.42
    POSITIVE LOGITS
     heart
    0.97
     hearts
    0.90
    heart
    0.83
    ❋
    0.81
     Heart
    0.77
     Hearts
    0.75
     HEART
    0.74
    hearts
    0.71
     star
    0.71
     butterfly
    0.69
    Activations Density 2.175%

    No Known Activations