© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8839
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with reports, findings, statements and research

    oai_token-act-pair · gemini-2.0-flash

    were

    np_max-act-logits · gemini-2.0-flash

    say "were"

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     was
    -1.17
    was
    -0.98
     Was
    -0.87
    Was
    -0.87
     wasn
    -0.75
    WAS
    -0.74
     WAS
    -0.73
     був
    -0.72
    GraphicsUnit
    -0.67
     Efq
    -0.66
    POSITIVE LOGITS
     were
    1.22
    Were
    0.93
    were
    0.83
     Were
    0.81
     WERE
    0.65
    sizeCache
    0.57
     मिले
    0.56
    loem
    0.54
     furent
    0.52
     BoxFit
    0.51
    Activations Density 5.433%

    No Known Activations