© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15530
    Prev
    Next
    INDEX
    Explanations

    code snippets that are likely android xml and json

    oai_token-act-pair · gemini-2.0-flash

    images

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    bori
    -0.42
    EditorBrowsable
    -0.41
    Vezi
    -0.40
    yecek
    -0.39
    ModelState
    -0.38
    DataMember
    -0.38
    mişti
    -0.38
    makeText
    -0.38
     Daly
    -0.37
    firi
    -0.37
    POSITIVE LOGITS
     image
    1.53
     picture
    1.37
     photo
    1.33
     Image
    1.29
    Image
    1.24
    image
    1.23
     photograph
    1.22
     images
    1.20
     IMAGE
    1.19
     imagen
    1.17
    Activations Density 1.227%

    No Known Activations