© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13828
    Prev
    Next
    INDEX
    Explanations

    phrases related to slavery, political power, and government

    oai_token-act-pair · gemini-2.0-flash

    political ideologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    oid
    -0.55
    onAttach
    -0.50
    homonymie
    -0.46
     Familienname
    -0.46
    ArgsConstructor
    -0.46
    kum
    -0.43
     съ
    -0.43
    AppCompat
    -0.42
    al
    -0.41
     Please
    -0.41
    POSITIVE LOGITS
    LookAnd
    0.81
    Демографія
    0.73
    GEBURTSDATUM
    0.70
    closePath
    0.69
    TypedDataSet
    0.67
     متعلقه
    0.67
     مرئيه
    0.63
    unmodifiable
    0.63
    improvement
    0.63
     Mejora
    0.63
    Activations Density 5.414%

    No Known Activations