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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1090
    Prev
    Next
    INDEX
    Explanations

    text describing firearms and ammunition

    oai_token-act-pair · gemini-2.0-flash

    guns and ammunition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     RUE
    -0.52
     yardımcı
    -0.49
    Referencies
    -0.47
     sanitaires
    -0.47
     senta
    -0.44
    transferase
    -0.44
    MPL
    -0.44
    Helmet
    -0.43
    برت
    -0.42
     Settlements
    -0.42
    POSITIVE LOGITS
     propOrder
    0.81
    BufferException
    0.71
    nsito
    0.62
    uxxxx
    0.60
    DeleteBehavior
    0.59
     tartalomajánló
    0.59
    InputTagHelper
    0.59
    CppCodeGen
    0.57
    afficheront
    0.57
    expandindo
    0.54
    Activations Density 0.942%

    No Known Activations