© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3865
    Prev
    Next
    INDEX
    Explanations

    text about pregnancy, birth, and infant health

    oai_token-act-pair · gemini-2.0-flash

    coding syntax and terminology

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

    childbirth

    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
     birth
    -1.50
     Birth
    -1.36
    birth
    -1.33
     born
    -1.30
    Birth
    -1.23
     BIRTH
    -1.20
     births
    -1.20
    born
    -1.11
     Born
    -1.10
    BIRTH
    -1.04
    POSITIVE LOGITS
    ."));
    0.51
    "}}
    0.51
     "));
    0.49
     rodziny
    0.44
    ExtendWith
    0.41
     '.')
    0.41
    StreetMap
    0.41
    Sabato
    0.41
    ="")
    0.40
    >');
    0.40
    Activations Density 0.550%

    No Known Activations