© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13458
    Prev
    Next
    INDEX
    Explanations

    descriptions of elements of the dining experience in a restaurant

    oai_token-act-pair · gemini-2.0-flash

    restaurants and food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    vábbi
    -0.54
    瘍
    -0.45
    нш
    -0.45
    parseFrom
    -0.44
     Ra
    -0.44
    떨
    -0.44
     facto
    -0.44
    ([],
    -0.43
    acle
    -0.43
     messy
    -0.43
    POSITIVE LOGITS
    SequentialGroup
    0.82
    +#+#
    0.67
    ConstraintMaker
    0.66
     fubject
    0.66
     resourceCulture
    0.64
     fhort
    0.61
    NameInMap
    0.57
    PositiveButton
    0.57
    ̀nh
    0.57
     iſt
    0.56
    Activations Density 0.727%

    No Known Activations