© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12650
    Prev
    Next
    INDEX
    Explanations

    pronouns and related words

    oai_token-act-pair · gemini-2.0-flash

    who

    np_max-act-logits · gemini-2.0-flash

    pronouns

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ActiveRecord
    -0.69
     hendes
    -0.62
    forRoot
    -0.61
     applies
    -0.60
    záll
    -0.59
     accumulates
    -0.59
    Хочу
    -0.58
    muje
    -0.56
     Applies
    -0.56
    .}(
    -0.56
    POSITIVE LOGITS
     depended
    1.04
     consisted
    1.02
     was
    0.93
     lacked
    0.92
     differed
    0.88
     belonged
    0.87
     corresponded
    0.86
     tended
    0.84
     had
    0.84
     stood
    0.83
    Activations Density 2.114%

    No Known Activations