© 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. 8672
    Prev
    Next
    INDEX
    Explanations

    words related to the intersection of culture and economics

    oai_token-act-pair · gemini-2.0-flash

    phrases related to cultural characteristics and community

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

    Vietnam locations

    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
    #+#
    -0.81
     itſelf
    -0.78
    RegressionTest
    -0.69
     Wikimédia
    -0.67
    fingers
    -0.65
     typelib
    -0.65
    NOPQRST
    -0.65
    AccessorTable
    -0.65
    rrggbb
    -0.62
    GenerationType
    -0.62
    POSITIVE LOGITS
     for
    0.51
     cor
    0.47
     imp
    0.47
     cực
    0.45
    ông
    0.45
    Version
    0.45
     em
    0.44
     mad
    0.44
     and
    0.44
     s
    0.44
    Activations Density 11.858%

    No Known Activations