© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12788
    Prev
    Next
    INDEX
    Explanations

    words or phrases that describe a task or activity as difficult and a burden

    oai_token-act-pair · gemini-2.0-flash

    Business processes and tasks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     curie
    -0.63
    انجليز
    -0.63
    InitVars
    -0.52
    ofluor
    -0.49
    广
    -0.48
    回路
    -0.45
    tshell
    -0.44
     المعيارى
    -0.43
    UnknownFieldSet
    -0.43
    yong
    -0.43
    POSITIVE LOGITS
     nakalista
    0.67
     BoxDecoration
    0.66
    @[+][
    0.66
    __":
    0.65
    msgTypes
    0.64
     américains
    0.64
    __':
    0.64
     médicaux
    0.63
    ViewFeatures
    0.62
     виправивши
    0.61
    Activations Density 0.638%

    No Known Activations