© 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. 8067
    Prev
    Next
    INDEX
    Explanations

    words related to politics, legality, genetic engineering, reproduction or social issues, sometimes with intensity

    oai_token-act-pair · gemini-2.0-flash

    adjacency to politically and socially charged terms

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

    societal themes

    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
    MigrationBuilder
    -0.92
     ExecuteAsync
    -0.90
    BufferException
    -0.83
    SourceChecksum
    -0.78
     kasarigan
    -0.74
    ंदीखरीदारी
    -0.69
     Roskov
    -0.69
    LookAnd
    -0.68
    webElementXpaths
    -0.66
    Datuak
    -0.65
    POSITIVE LOGITS
    }^{+\
    0.52
     inevitable
    0.52
     acceptable
    0.52
     costly
    0.51
     popular
    0.51
     attractive
    0.50
     convenient
    0.49
    toupper
    0.48
     incompatible
    0.48
     rigorous
    0.47
    Activations Density 2.606%

    No Known Activations