© 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. 4787
    Prev
    Next
    INDEX
    Explanations

    language, numbers, and symbols that represent data values and figure or table references

    oai_token-act-pair · gemini-2.0-flash

    numerical values

    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
     value
    -2.91
    value
    -2.64
     Value
    -2.61
    Value
    -2.44
     VALUE
    -2.33
    VALUE
    -2.02
     valeur
    -1.96
     valore
    -1.62
     Wert
    -1.59
     waarde
    -1.55
    POSITIVE LOGITS
     Paglinawan
    0.64
     AspNetCore
    0.56
    anskje
    0.55
    yntaxException
    0.52
    ctibles
    0.51
     opérateur
    0.51
    ArrowToggle
    0.48
    =$?
    0.47
    ">//
    0.47
    ніципа
    0.46
    Activations Density 5.134%

    No Known Activations