© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4884
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to political revolution or trade unions, and programming-related items like HTTP requests and directories

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ystis
    -0.50
     resultCode
    -0.48
    ೕ
    -0.46
     cooperativa
    -0.45
    initState
    -0.44
     itinéraires
    -0.44
     intptr
    -0.44
    polis
    -0.43
    {//
    -0.43
     Hacks
    -0.43
    POSITIVE LOGITS
    íqu
    0.73
    Datuak
    0.72
    TagMode
    0.68
    tagHelperRunner
    0.66
    ГЛА
    0.66
     ویکی‌پدیای
    0.65
     مشين
    0.65
    írus
    0.65
    ReusableCell
    0.63
     تضيفلها
    0.63
    Activations Density 3.442%

    No Known Activations