© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7249
    Prev
    Next
    INDEX
    Explanations

    text about golf or physically carrying something

    oai_token-act-pair · gemini-2.0-flash

    cases / case

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     betweenstory
    -0.77
    +#+#
    -0.71
     pack
    -0.71
     препратки
    -0.70
     Pack
    -0.69
     مشين
    -0.67
    Datuak
    -0.67
     Chwiliwch
    -0.66
    PACK
    -0.66
    Pack
    -0.65
    POSITIVE LOGITS
     cases
    0.50
     case
    0.50
     Case
    0.46
    hard
    0.45
     spinners
    0.43
     trolley
    0.43
    ابراین
    0.43
     Hard
    0.41
    case
    0.41
     hard
    0.41
    Activations Density 0.890%

    No Known Activations