© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4006
    Prev
    Next
    INDEX
    Explanations

    instances of raising children in a religious context, or paying for youth activities

    oai_token-act-pair · gemini-2.0-flash

    private

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Educ
    -0.65
    MLLoader
    -0.59
     Teaching
    -0.59
    Teaching
    -0.58
     TEACHING
    -0.57
     EDUCATION
    -0.57
     educ
    -0.56
    TestTools
    -0.56
     teaching
    -0.55
    Educ
    -0.54
    POSITIVE LOGITS
     private
    1.23
     Private
    1.01
    Private
    1.00
    private
    0.95
     privé
    0.94
     privée
    0.90
    PRIVATE
    0.89
     PRIVATE
    0.88
     privada
    0.86
     privées
    0.84
    Activations Density 1.754%

    No Known Activations