© 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. 2074
    Prev
    Next
    INDEX
    Explanations

    words related to academic research studies

    oai_token-act-pair · gemini-2.0-flash

    describing inherent qualities

    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
    verwijspagina
    -1.18
     lenker
    -1.08
     pinulongan
    -1.06
    MessageTagHelper
    -1.00
     noDo
    -0.98
    IsMutable
    -0.97
    ⓧ
    -0.96
    ViewImports
    -0.96
    RenderAtEndOf
    -0.96
     kasarigan
    -0.94
    POSITIVE LOGITS
     tasca
    0.39
     even
    0.39
     enf
    0.39
    ほど
    0.39
     même
    0.38
     
    0.38
     alternativa
    0.37
    jska
    0.37
    '
    0.36
    <eos>
    0.36
    Activations Density 43.303%

    No Known Activations