© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 145
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to code and software development, including some medical terms like receptors

    oai_token-act-pair · gemini-2.0-flash

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     with
    -2.59
    with
    -1.87
     avec
    -1.80
     dengan
    -1.73
     với
    -1.60
    avec
    -1.39
     עם
    -1.33
     WITH
    -1.32
    With
    -1.27
     با
    -1.25
    POSITIVE LOGITS
     nakalista
    0.66
     Walkover
    0.65
     surla
    0.63
    ruptedException
    0.57
    󠁬
    0.54
    sizeCache
    0.53
     saites
    0.53
    Wi
    0.53
    })`
    0.53
    AddTagHelper
    0.52
    Activations Density 2.738%

    No Known Activations