© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8387
    Prev
    Next
    INDEX
    Explanations

    this neuron appears to activate on many common words in a sentence

    oai_token-act-pair · gemini-2.0-flash

    Number three

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     two
    -1.12
     Two
    -1.11
    Two
    -1.09
    two
    -1.02
     deux
    -0.91
    TWO
    -0.86
     TWO
    -0.84
     Kedua
    -0.84
     Deux
    -0.82
     dois
    -0.80
    POSITIVE LOGITS
     trio
    1.34
     tri
    1.19
     three
    1.17
    三
    1.17
     triple
    1.16
    3
    1.13
    three
    1.07
     trilogy
    1.06
    triple
    1.05
     ketiga
    1.05
    Activations Density 2.352%

    No Known Activations