© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5072
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to children and legal situations

    oai_token-act-pair · gemini-2.0-flash

    child/birth context

    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
    -1.12
     girls
    -1.10
    children
    -1.05
    Children
    -1.00
     kids
    -0.99
     Children
    -0.98
     babies
    -0.97
     CHILDREN
    -0.96
     Girls
    -0.95
    Girls
    -0.95
    POSITIVE LOGITS
     Advisors
    0.47
     OMIT
    0.44
    Formats
    0.43
    ῃ
    0.42
     hozzá
    0.41
     esperti
    0.41
    irsten
    0.40
     Realtors
    0.40
     eksemp
    0.39
    ễ
    0.39
    Activations Density 3.166%

    No Known Activations