© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10489
    Prev
    Next
    INDEX
    Explanations

    the word "kid"

    oai_token-act-pair · gemini-2.0-flash

    kid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     kids
    -1.62
     kid
    -1.52
    kids
    -1.48
     Kids
    -1.36
    Kids
    -1.34
     KIDS
    -1.23
    kid
    -1.05
    Kid
    -1.01
     KID
    -0.95
     Kid
    -0.94
    POSITIVE LOGITS
    <bos>
    0.67
     breath
    0.66
     breathe
    0.49
     Breath
    0.48
     breathing
    0.46
    breath
    0.46
    getSystemService
    0.46
     Kombat
    0.45
    úrese
    0.44
    RequestMapping
    0.42
    Activations Density 0.255%

    No Known Activations