© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9454
    Prev
    Next
    INDEX
    Explanations

    phrases that have "the" flanked by prepositions

    oai_token-act-pair · gemini-2.0-flash

    hyphens and dashes

    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
     avoient
    -1.55
     normaux
    -1.52
     démocr
    -1.50
     fermés
    -1.48
     scolaires
    -1.47
     étoient
    -1.43
     automatiques
    -1.43
     feroit
    -1.42
     définiti
    -1.38
     supérieurs
    -1.36
    POSITIVE LOGITS
    -
    0.80
    –
    0.73
    ‐
    0.71
     -
    0.69
     “
    0.68
    ‑
    0.63
    ­
    0.62
    -​
    0.59
    --
    0.58
    −
    0.57
    Activations Density 22.172%

    No Known Activations