© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7482
    Prev
    Next
    INDEX
    Explanations

    the word "as" and often the words "well", "physical", or "spiritual" nearby

    oai_token-act-pair · gemini-2.0-flash

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     well
    -3.02
    well
    -2.83
     Well
    -2.80
    Well
    -2.78
     WELL
    -2.67
    WELL
    -2.58
     bien
    -2.22
    wells
    -2.02
     wells
    -1.95
     WELLS
    -1.61
    POSITIVE LOGITS
     Référence
    0.59
    DotNetBar
    0.56
    ädie
    0.56
     springfox
    0.54
    ГЛА
    0.53
     kasarigan
    0.52
    tiliz
    0.52
    γη
    0.50
    vdots
    0.50
    ArgsConstructor
    0.49
    Activations Density 3.576%

    No Known Activations