© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 165
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to scientific or technical writing and jargon.

    oai_token-act-pair · gemini-2.0-flash

    styles and types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ตะ
    -0.50
    новниш
    -0.47
    '__
    -0.45
    ządu
    -0.45
     Drapeau
    -0.44
     sternum
    -0.43
     ampoule
    -0.42
     joie
    -0.42
     reactivity
    -0.42
    wel
    -0.42
    POSITIVE LOGITS
     ***!
    0.77
    PYX
    0.71
     autorytatywna
    0.68
    SourceChecksum
    0.66
    deelte
    0.66
    BufferException
    0.66
     saites
    0.65
     /\.(
    0.64
    EndProject
    0.62
    jspb
    0.60
    Activations Density 4.523%

    No Known Activations