© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5250
    Prev
    Next
    INDEX
    Explanations

    the word "medium" followed by a word indicating the size of something

    oai_token-act-pair · gemini-2.0-flash

    medium

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    Kjelder
    -0.70
     bambú
    -0.63
    ContentAsync
    -0.63
     terciopelo
    -0.60
     kontra
    -0.56
    NavController
    -0.55
    SceneManagement
    -0.54
    MLLoader
    -0.54
     fieltro
    -0.53
    archiviato
    -0.53
    POSITIVE LOGITS
    fjspx
    0.56
     ब्रेकडाउन
    0.54
    IntoConstraints
    0.50
    webElementXpaths
    0.50
     betweenstory
    0.50
     time
    0.48
     Superhost
    0.47
    vacy
    0.46
    PageIndex
    0.46
    atyw
    0.46
    Activations Density 4.143%

    No Known Activations