© 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. 4987
    Prev
    Next
    INDEX
    Explanations

    clinical or social care settings and services for addiction and related mental health conditions

    oai_token-act-pair · gemini-2.0-flash

    Community or medical assistance

    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
    AndEndTag
    -0.70
    ernalia
    -0.62
    ulents
    -0.60
     становника
    -0.60
    PhysRev
    -0.59
    uegos
    -0.59
    '])){
    -0.57
     MenuView
    -0.57
    енча
    -0.56
    MENAFN
    -0.56
    POSITIVE LOGITS
     ComVisible
    0.54
    partial
    0.48
    CodeDom
    0.46
    contentLoaded
    0.44
    onoi
    0.43
    Referanser
    0.43
     Partial
    0.42
    COMP
    0.42
     Aceite
    0.42
    nem
    0.41
    Activations Density 3.898%

    No Known Activations