© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2780
    Prev
    Next
    INDEX
    Explanations

    text related to United States national or state politics

    oai_token-act-pair · gemini-2.0-flash

    American politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ValueStyle
    -0.56
    intenance
    -0.54
    fillText
    -0.52
    uby
    -0.52
    mlar
    -0.47
     loadData
    -0.47
     Handeln
    -0.47
     rythme
    -0.46
     lápiz
    -0.46
    oves
    -0.45
    POSITIVE LOGITS
    +#+
    0.73
     Parliament
    0.64
    celotti
    0.63
    AntiForgeryToken
    0.62
    principalTable
    0.61
    titleMargin
    0.60
     SwitchCompat
    0.59
     ✭✭
    0.59
     Presidential
    0.58
     defStyleAttr
    0.58
    Activations Density 5.745%

    No Known Activations