© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8178
    Prev
    Next
    INDEX
    Explanations

    the word "this", and sometimes words that commonly follow it

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     this
    -1.52
     myſelf
    -1.43
    BibitemShut
    -1.41
     itſelf
    -1.33
     Efq
    -1.30
    neſs
    -1.29
     whoſe
    -1.26
     becauſe
    -1.26
    ^(@)
    -1.23
     theſe
    -1.23
    POSITIVE LOGITS
    1
    0.87
    S
    0.79
    5
    0.78
    X
    0.78
    4
    0.77
    "
    0.77
    c
    0.77
    x
    0.75
    6
    0.75
    *
    0.75
    Activations Density 0.488%

    No Known Activations