© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8605
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to childcare, parental involvement and legal defenses, particularly in the context of child abuse and child nutrition.

    oai_token-act-pair · gemini-2.0-flash

    children

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     children
    -2.73
     Children
    -2.72
     child
    -2.69
    Children
    -2.67
     Child
    -2.59
     kids
    -2.56
    Child
    -2.53
     Kids
    -2.53
    children
    -2.50
    Kids
    -2.47
    POSITIVE LOGITS
    tellungs
    0.41
    ajoz
    0.39
    новниш
    0.38
    allon
    0.38
    akyti
    0.38
     battu
    0.37
    '/',
    0.37
    onych
    0.36
    urgo
    0.36
     monasterio
    0.35
    Activations Density 2.144%

    No Known Activations