© 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. 4113
    Prev
    Next
    INDEX
    Explanations

    mentions of schools and universities, particularly their names

    oai_token-act-pair · gemini-2.0-flash

    Academic studies

    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
    Not in Any Lists

    No Comments

    Negative Logits
    BagConstraints
    -0.71
    AddTagHelper
    -0.71
    fjspx
    -0.67
    canestro
    -0.64
    GEBURTSDATUM
    -0.64
     JpaRepository
    -0.63
    kháu
    -0.63
    例句
    -0.61
    writeFieldEnd
    -0.61
    ContentAsync
    -0.60
    POSITIVE LOGITS
     divisão
    0.54
    Activator
    0.52
     sintético
    0.52
    problema
    0.52
    donor
    0.52
     faixa
    0.52
    ようと
    0.52
    ticoli
    0.52
     ruolo
    0.49
    honneur
    0.49
    Activations Density 7.365%

    No Known Activations