© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10425
    Prev
    Next
    INDEX
    Explanations

    words or phrases from a variety of languages, including Spanish, French and Javascript.

    oai_token-act-pair · gemini-2.0-flash

    words related to diverse organizations or entities

    np_token-act-pair-logits · gpt-4o-mini

    mixed languages/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     los
    -0.91
     those
    -0.91
     dei
    -0.88
     các
    -0.88
     dels
    -0.85
     των
    -0.84
    those
    -0.84
     des
    -0.82
     degli
    -0.79
     les
    -0.78
    POSITIVE LOGITS
     démocr
    0.65
    AddTagHelper
    0.63
     chré
    0.59
     sauvages
    0.58
     fédé
    0.56
     colorés
    0.54
     appartiennent
    0.54
     policiales
    0.54
     normaux
    0.54
     diterima
    0.53
    Activations Density 0.417%

    No Known Activations