© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10834
    Prev
    Next
    INDEX
    Explanations

    technical writing that contains logical relationships and 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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    出版年
    -0.76
    ValueStyle
    -0.73
    ArrowToggle
    -0.69
    AddTagHelper
    -0.68
     estimés
    -0.68
    تقاوى
    -0.67
     otomatig
    -0.64
    WithIOException
    -0.63
     للمعارف
    -0.62
    WriteAttribute
    -0.61
    POSITIVE LOGITS
     Tempe
    0.43
    Coro
    0.43
    ppen
    0.43
    kmäler
    0.42
     BrowserModule
    0.41
     tady
    0.41
    vende
    0.41
    Full
    0.40
    only
    0.40
    Only
    0.40
    Activations Density 3.969%

    No Known Activations