© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2598
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to elections and political parties.

    oai_token-act-pair · gemini-2.0-flash

    elections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    expandindo
    -0.61
     mergeFrom
    -0.56
    +#+#
    -0.55
    béco
    -0.54
     err
    -0.54
    oa̍t
    -0.52
    ckeye
    -0.52
    adget
    -0.50
    IBOutlet
    -0.49
     okuyayım
    -0.49
    POSITIVE LOGITS
    ArgumentParser
    0.59
     esternos
    0.57
    ξεις
    0.57
    ActionCreators
    0.55
    DispatchToProps
    0.55
    UnusedPrivate
    0.53
     BIL
    0.51
     Wör
    0.50
    XmlAccessorType
    0.50
     rendezvous
    0.49
    Activations Density 0.378%

    No Known Activations