Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14585
    Prev
    Next
    INDEX
    Explanations

    negative numbers following a dash

    oai_token-act-pair · gemini-2.0-flash

    code and equations

    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
    ούν
    -0.50
     morire
    -0.40
     Obj
    -0.40
    nalité
    -0.40
    mona
    -0.40
    მ
    -0.39
    readObject
    -0.39
    ής
    -0.38
    лович
    -0.38
    meaux
    -0.38
    POSITIVE LOGITS
    WebVitals
    0.91
    enumi
    0.82
     يتيمه
    0.75
    invokeLater
    0.75
    TagMode
    0.74
     Preferencias
    0.74
    AnchorTagHelper
    0.73
     AssemblyVersion
    0.69
     InputDecoration
    0.68
     الرياضيه
    0.68
    Activations Density 2.813%

    No Known Activations