© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13623
    Prev
    Next
    INDEX
    Explanations

    instances of pronouns and words related to sales

    oai_token-act-pair · gemini-2.0-flash

    broad, general texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Населення
    -0.52
    contentLoaded
    -0.51
    woj
    -0.47
     puntas
    -0.45
    warran
    -0.44
     soltanto
    -0.43
     Fai
    -0.43
    providedIn
    -0.43
    addCriterion
    -0.42
    ENAS
    -0.42
    POSITIVE LOGITS
     مواليد
    0.68
     wireType
    0.66
     []:
    0.65
    FieldBuilder
    0.63
    ilarang
    0.61
    :+:
    0.58
    qrstuvwxyz
    0.58
    FieldNumber
    0.57
    WriteTagHelper
    0.56
    ergies
    0.55
    Activations Density 3.357%

    No Known Activations