© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12208
    Prev
    Next
    INDEX
    Explanations

    mentions of the politicians Newt Gingrich and Rick Santorum as well as words associated with politics

    oai_token-act-pair · gemini-2.0-flash

    Gingrich and Santorum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    クリル
    -0.54
     граждан
    -0.41
     Dames
    -0.40
     Marchand
    -0.40
     adatt
    -0.39
     차
    -0.39
     ekstra
    -0.38
     euch
    -0.38
    >{@
    -0.38
     CAPITAL
    -0.37
    POSITIVE LOGITS
    <bos>
    0.93
    featureID
    0.82
     ThemeData
    0.76
    +#+#
    0.75
     estekak
    0.72
    adaptiveStyles
    0.71
    TestingModule
    0.69
    Personendaten
    0.66
     Efq
    0.66
     uſe
    0.66
    Activations Density 1.495%

    No Known Activations