© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7841
    Prev
    Next
    INDEX
    Explanations

    substrings "civar" or similar followed by a 1-2 digit number, or words related to URLs or email addresses in other languages

    oai_token-act-pair · gemini-2.0-flash

    ci

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     nakalista
    -0.75
     citizen
    -0.63
    citizens
    -0.61
     تضيفلها
    -0.61
    citizen
    -0.59
     EconPapers
    -0.59
     Administrativna
    -0.59
     TestBed
    -0.58
    ici
    -0.58
     anzunehmen
    -0.57
    POSITIVE LOGITS
    ISupport
    0.57
    principalColumn
    0.49
     απε
    0.48
    devamını
    0.46
    UrlResolution
    0.46
     Bourgoin
    0.45
     Савезне
    0.44
     inflater
    0.44
     Kandy
    0.43
     bậc
    0.42
    Activations Density 7.716%

    No Known Activations