© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11860
    Prev
    Next
    INDEX
    Explanations

    proper nouns and associated pronouns and verbs

    oai_token-act-pair · gemini-2.0-flash

    past tense verbs

    np_token-act-pair-logits · gpt-4o-mini

    "was" in other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     disambiguazione
    -0.79
     selected
    -0.76
     hired
    -0.74
     invited
    -0.69
     hire
    -0.68
     propOrder
    -0.66
     recruited
    -0.66
     appointed
    -0.64
     select
    -0.64
     invite
    -0.63
    POSITIVE LOGITS
     werd
    0.84
    被
    0.75
     được
    0.73
     venne
    0.72
    就被
    0.70
     was
    0.67
     wurde
    0.64
     wordt
    0.64
     worden
    0.63
    也被
    0.62
    Activations Density 1.885%

    No Known Activations