© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8180
    Prev
    Next
    INDEX
    Explanations

    terms and phrases used in political and social commentary, often referencing specific groups, ideologies, or historical events

    oai_token-act-pair · gemini-2.0-flash

    race and politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     <=",
    -0.79
    onAttach
    -0.71
    LookAnd
    -0.68
     الاطلاع
    -0.66
    dersfield
    -0.64
     linkovi
    -0.58
    InitVars
    -0.57
     Réponses
    -0.57
    rhosis
    -0.56
    migrationBuilder
    -0.55
    POSITIVE LOGITS
    viewDidLoad
    0.54
     QWidget
    0.52
    ÇA
    0.51
     independent
    0.48
     CURIAM
    0.48
     zelfs
    0.46
     index
    0.43
     indépend
    0.43
    ERAL
    0.42
    idł
    0.42
    Activations Density 6.255%

    No Known Activations