© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15826
    Prev
    Next
    INDEX
    Explanations

    conjunctions and discourse markers

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    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
     Are
    -0.77
     Is
    -0.66
     Its
    -0.62
    Are
    -0.59
     Can
    -0.50
     They
    -0.49
    <bos>
    -0.48
    Its
    -0.47
     Was
    -0.47
    Is
    -0.47
    POSITIVE LOGITS
     Jefus
    1.05
     myſelf
    0.97
     pleaſure
    0.96
     purpoſe
    0.94
     Efq
    0.92
     reaſon
    0.91
     Cæsar
    0.90
     ſtate
    0.89
     Majefty
    0.88
     greateſt
    0.87
    Activations Density 12.590%

    No Known Activations