© 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. 1346
    Prev
    Next
    INDEX
    Explanations

    a mix of html/mathematical notation and location references

    oai_token-act-pair · 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
     
    -0.48
    tis
    -0.46
     W
    -0.46
    bukkit
    -0.44
    jfree
    -0.44
    BASEPATH
    -0.44
     les
    -0.43
     la
    -0.42
     doGet
    -0.42
     T
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.87
     fevere
    0.85
    Билгалдахарш
    0.84
     fidé
    0.81
    ſelves
    0.81
     <=",
    0.80
     Reſ
    0.80
     étoient
    0.79
     Majefty
    0.79
     démocr
    0.79
    Activations Density 0.435%

    No Known Activations