© 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. 7596
    Prev
    Next
    INDEX
    Explanations

    words and syllables that start with "de", "re", or "sub" sometimes in a medical or political context

    oai_token-act-pair · gemini-2.0-flash

    Prefixes

    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
    writeFieldEnd
    -0.65
    rungsseite
    -0.59
     <=",
    -0.58
     ویکی‌پدی
    -0.57
     StringTokenizer
    -0.55
     percolation
    -0.54
     Bonding
    -0.54
     Seeder
    -0.54
     informée
    -0.53
     مشين
    -0.52
    POSITIVE LOGITS
     Ubi
    0.52
    ImageContext
    0.48
    ientí
    0.48
     connais
    0.48
    RequiresApi
    0.48
    publ
    0.47
     pauvre
    0.46
     pobre
    0.46
    BASEPATH
    0.46
    hamburg
    0.45
    Activations Density 7.660%

    No Known Activations