© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12254
    Prev
    Next
    INDEX
    Explanations

    the word "to" and words directly preceding or following it

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     nahilalakip
    -0.72
    modelBuilder
    -0.60
    UnsafeEnabled
    -0.59
    OrBuilder
    -0.57
    MigrationBuilder
    -0.56
    lijkheid
    -0.56
    NameInMap
    -0.55
    omock
    -0.54
    CreateModel
    -0.54
    FailureListener
    -0.54
    POSITIVE LOGITS
     otomatig
    0.57
     estekak
    0.55
    addContainerGap
    0.52
    OIR
    0.51
     ſtate
    0.47
     Yarm
    0.47
     linkovi
    0.46
    findpost
    0.46
     gewe
    0.45
     mevcut
    0.44
    Activations Density 5.111%

    No Known Activations