© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13709
    Prev
    Next
    INDEX
    Explanations

    words related to a scientific experiment or sporting event

    oai_token-act-pair · gemini-2.0-flash

    trials

    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
     disambiguazione
    -0.45
    destroyAll
    -0.45
    ทย
    -0.43
     maravillas
    -0.42
     climatique
    -0.42
    nyv
    -0.42
    TagHelpers
    -0.42
     gesetz
    -0.41
     oreilles
    -0.41
     portátiles
    -0.41
    POSITIVE LOGITS
    IsContent
    0.78
     inning
    0.70
    numerusform
    0.68
     Мексичка
    0.68
    SBATCH
    0.66
    StoryboardSegue
    0.65
    frameCount
    0.65
    <bos>
    0.65
    ագրություններ
    0.64
     minute
    0.63
    Activations Density 1.932%

    No Known Activations