© 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. 13342
    Prev
    Next
    INDEX
    Explanations

    words related to educational materials for children

    oai_token-act-pair · gemini-2.0-flash

    words related to children

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

    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_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
     ſtate
    -0.62
     calldata
    -0.56
     ſeveral
    -0.52
     Theſe
    -0.52
     myſelf
    -0.52
     becauſe
    -0.52
     ſhe
    -0.50
     Monfieur
    -0.50
     CommandType
    -0.50
     Houſe
    -0.50
    POSITIVE LOGITS
     children
    1.94
     kids
    1.87
     Children
    1.68
     child
    1.66
     Kids
    1.66
    kids
    1.65
    Children
    1.62
    Kids
    1.61
    children
    1.61
     kid
    1.60
    Activations Density 5.802%

    No Known Activations