© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6216
    Prev
    Next
    INDEX
    Explanations

    a variety of function words, words that end in "ly", and words that are used subjectively to describe an event

    oai_token-act-pair · gemini-2.0-flash

    indeed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    rehensible
    -0.56
    partial
    -0.49
     ais
    -0.49
    „
    -0.49
    äsident
    -0.48
    «
    -0.48
     REI
    -0.47
    arp
    -0.47
    «.
    -0.47
     rond
    -0.47
    POSITIVE LOGITS
     debout
    0.79
     feroit
    0.77
     figliu
    0.74
    Referanser
    0.72
     discorso
    0.71
     câte
    0.70
     écout
    0.70
     doucement
    0.69
    Referències
    0.69
     chré
    0.68
    Activations Density 7.244%

    No Known Activations