© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11574
    Prev
    Next
    INDEX
    Explanations

    similes which contain the word "like"

    oai_token-act-pair · gemini-2.0-flash

    like or a

    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
    dAtA
    -0.56
     lenker
    -0.56
    protoimpl
    -0.54
    Демографія
    -0.54
     transférez
    -0.52
     MaterialApp
    -0.50
     multiply
    -0.50
    enumi
    -0.50
     beginnetje
    -0.49
    ьаж
    -0.46
    POSITIVE LOGITS
    AnimationsModule
    0.64
    例文帳に追加
    0.56
     שוליים
    0.54
    EndContext
    0.53
    aard
    0.53
    usepackage
    0.51
    apunov
    0.50
    Geplaatst
    0.49
    jacks
    0.48
     Grandmother
    0.48
    Activations Density 1.052%

    No Known Activations