© 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. 90
    Prev
    Next
    INDEX
    Explanations

    code, law and medical terminology

    oai_token-act-pair · gemini-2.0-flash

    technical documentation/code

    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
     intptr
    -0.42
    AddTagHelper
    -0.41
    oa̍t
    -0.39
    хьтан
    -0.38
    得意
    -0.36
     worldwide
    -0.36
     harina
    -0.36
    ☚
    -0.35
    verre
    -0.34
     interpr
    -0.34
    POSITIVE LOGITS
    tonode
    0.90
    onViewCreated
    0.80
    StoryboardSegue
    0.75
     Monfieur
    0.71
    Datuak
    0.70
     Efq
    0.69
    WriteBarrier
    0.68
     voici
    0.68
    ValueStyle
    0.65
    IntoConstraints
    0.65
    Activations Density 11.544%

    No Known Activations