© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14434
    Prev
    Next
    INDEX
    Explanations

    academic writing about physics and advanced mathematics

    oai_token-act-pair · gemini-2.0-flash

    scientific systems

    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
     EconPapers
    -0.81
     >=",
    -0.78
    webElementXpaths
    -0.68
    出版年
    -0.61
    ValueGeneration
    -0.56
    #+#
    -0.55
    VolleyError
    -0.55
     kaynağından
    -0.54
    SharedDtor
    -0.54
    PYX
    -0.53
    POSITIVE LOGITS
    enser
    0.56
    hae
    0.54
    ributed
    0.52
    ystems
    0.50
    olving
    0.50
    |<\
    0.50
     étroite
    0.48
    Configurer
    0.48
     inférieure
    0.48
     eivät
    0.48
    Activations Density 29.564%

    No Known Activations