© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10423
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies, especially involving catalysts, reactions, and assays

    oai_token-act-pair · gemini-2.0-flash

    Specificity/activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    awtextra
    -0.55
    脚注の使い方
    -0.52
    sequelize
    -0.52
    viewDid
    -0.50
    BeforeClass
    -0.48
    Hochspringen
    -0.47
     مشين
    -0.47
     nothing
    -0.45
    ьа
    -0.45
    numerusform
    -0.45
    POSITIVE LOGITS
    pushFollow
    0.75
    Và
    0.68
    mainen
    0.66
    GIVEREF
    0.64
    állítás
    0.63
    SBATCH
    0.60
     Adagio
    0.59
    raszamy
    0.59
     Gees
    0.58
    experimental
    0.58
    Activations Density 4.470%

    No Known Activations