© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14410
    Prev
    Next
    INDEX
    Explanations

    words and phrases involving youth like children and childhood, and sometimes places frequented by them and items associated with them

    oai_token-act-pair · gemini-2.0-flash

    children

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     follic
    -0.50
    openConnection
    -0.48
    iteracy
    -0.47
    licator
    -0.46
    bigsqcup
    -0.46
    hells
    -0.46
     Mahal
    -0.45
    RenderAtEndOf
    -0.45
    tivation
    -0.45
    chiha
    -0.44
    POSITIVE LOGITS
     children
    0.96
     Children
    0.92
     CHILDREN
    0.92
    Children
    0.90
     child
    0.86
    CHILDREN
    0.85
    children
    0.84
     kids
    0.82
    Geplaatst
    0.80
     CHILD
    0.79
    Activations Density 1.801%

    No Known Activations