© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8330
    Prev
    Next
    INDEX
    Explanations

    text related to voting, contests, and getting involved

    oai_token-act-pair · gemini-2.0-flash

    until

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     AssemblyCulture
    -0.73
    LookAnd
    -0.68
    ViewById
    -0.67
     ujednoznacz
    -0.66
    intios
    -0.65
    tagHelper
    -0.64
    
    -0.63
    hyrchwyd
    -0.63
    parsedMessage
    -0.60
    oredCriteria
    -0.59
    POSITIVE LOGITS
     until
    1.74
    until
    1.60
     till
    1.48
    Until
    1.46
     Until
    1.45
     jusqu
    1.36
     UNTIL
    1.31
     untill
    1.27
    Till
    1.20
     până
    1.20
    Activations Density 1.138%

    No Known Activations