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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1127
    Prev
    Next
    INDEX
    Explanations

    bibliographic references and publication details

    oai_token-act-pair · gemini-2.0-flash

    bibliography

    np_token-act-pair-logits · gemini-2.0-flash

    Edited academic publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    offsetof
    -0.47
    వు
    -0.47
    ClientRect
    -0.38
     brancas
    -0.38
     stanie
    -0.38
    seido
    -0.38
     Punjab
    -0.38
    maz
    -0.38
     Merle
    -0.38
     turns
    -0.37
    POSITIVE LOGITS
    GEBURTSDATUM
    1.14
    findpost
    0.96
     autorytatywna
    0.87
     onCreateView
    0.79
    dafx
    0.77
    ########.
    0.77
    didSet
    0.75
    ThroughAttribute
    0.74
     Савезне
    0.70
     виправивши
    0.68
    Activations Density 1.471%

    No Known Activations