© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 627
    Prev
    Next
    INDEX
    Explanations

    mentions of politically sensitive topics like intelligence agencies, space, and medicine

    oai_token-act-pair · gemini-2.0-flash

    space

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    AndEndTag
    -0.87
    WriteTagHelper
    -0.70
     kaarangay
    -0.68
    脚注の使い方
    -0.66
    enumi
    -0.66
    ViewImports
    -0.65
    SizeF
    -0.64
    NameInMap
    -0.63
     estekak
    -0.63
    webElementXpaths
    -0.62
    POSITIVE LOGITS
     TestBed
    0.53
     primavera
    0.49
     constexpr
    0.48
     Richelieu
    0.46
     movements
    0.46
    arakhand
    0.46
    üyada
    0.44
    ర్య
    0.44
     combineReducers
    0.43
    istisches
    0.43
    Activations Density 20.305%

    No Known Activations