© 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. 9881
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "to be" and related concepts.

    oai_token-act-pair · gemini-2.0-flash

    Technical/formal language

    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
     holding
    -0.75
    tagHelperRunner
    -0.71
    Holding
    -0.69
     keeping
    -0.68
     Comes
    -0.66
    IUrlHelper
    -0.66
     Holding
    -0.66
     caring
    -0.66
     storing
    -0.64
     offering
    -0.63
    POSITIVE LOGITS
    autoIncrement
    0.54
     imageNamed
    0.54
     vulgaires
    0.52
    WriteAttribute
    0.49
    uterie
    0.47
    ithin
    0.47
     Leeuwen
    0.47
     synes
    0.46
    toft
    0.45
    ότητα
    0.44
    Activations Density 13.264%

    No Known Activations