© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 739
    Prev
    Next
    INDEX
    Explanations

    words that indicate smallness in quantity, time, or importance

    oai_token-act-pair · gemini-2.0-flash

    only/just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.51
    opposed
    -0.49
     Wikimédia
    -0.48
    toEqual
    -0.47
     Sabha
    -0.46
    kkue
    -0.46
    couvrir
    -0.45
     trocken
    -0.44
     drauf
    -0.43
     tibur
    -0.43
    POSITIVE LOGITS
    脚注の使い方
    0.88
     autorytatywna
    0.85
     resourceCulture
    0.76
     EconPapers
    0.69
    Hochspringen
    0.66
    RenderAtEndOf
    0.66
    AndEndTag
    0.64
    endpush
    0.64
    AlterField
    0.64
    ioutil
    0.63
    Activations Density 2.561%

    No Known Activations