© 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. 11307
    Prev
    Next
    INDEX
    Explanations

    content that looks like mathematical formatting

    oai_token-act-pair · gemini-2.0-flash

    technical terms or codes

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

    scientific/mathematical notation

    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
     taglia
    -0.49
     stället
    -0.48
     difficiles
    -0.47
     réfrig
    -0.47
     morire
    -0.46
     mélang
    -0.46
     assoluto
    -0.46
     verticales
    -0.46
     bará
    -0.45
     blessure
    -0.45
    POSITIVE LOGITS
    contentLoaded
    0.77
     يتيمه
    0.76
     चीज़ों
    0.75
    TagMode
    0.73
    tvguidetime
    0.68
    Hochspringen
    0.67
    Gön
    0.65
    GenerationType
    0.63
    aarrggbb
    0.62
    ")==
    0.62
    Activations Density 3.316%

    No Known Activations