© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7592
    Prev
    Next
    INDEX
    Explanations

    medical research labs or research hospitals that work with children

    oai_token-act-pair · gemini-2.0-flash

    mentions of "Children"

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

    childhood illnesses

    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
     SwitchCompat
    -0.47
     Devonshire
    -0.46
    первых
    -0.45
     mouth
    -0.44
     budding
    -0.42
    necked
    -0.42
    AccessorTable
    -0.42
    庁
    -0.42
    enumi
    -0.42
    فاظ
    -0.41
    POSITIVE LOGITS
     Children
    0.71
    Parcelize
    0.66
    Children
    0.66
    CHILDREN
    0.66
    ConstraintMaker
    0.63
     CHILDREN
    0.63
    childrens
    0.62
    Sucesor
    0.59
     pa
    0.58
     Egl
    0.57
    Activations Density 2.073%

    No Known Activations