© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7989
    Prev
    Next
    INDEX
    Explanations

    political text, with emphasis on the words "the", "of", "to", "and", or "a", followed by discussion or negative commentary

    oai_token-act-pair · gemini-2.0-flash

    words related to political or social movements

    np_token-act-pair-logits · gpt-4o-mini

    American politics and social issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RegressionTest
    -0.66
     يتيمه
    -0.64
    DockStyle
    -0.64
     Shakspeare
    -0.60
     EconPapers
    -0.59
     juſ
    -0.59
    antaranya
    -0.58
     fubject
    -0.58
    DoubleQuotes
    -0.57
     imprimée
    -0.57
    POSITIVE LOGITS
     anti
    0.60
    帖最后由
    0.56
    unchecked
    0.55
     pet
    0.52
    osoba
    0.49
     id
    0.49
    anti
    0.49
     cancel
    0.49
     type
    0.48
     Big
    0.48
    Activations Density 4.073%

    No Known Activations