© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11457
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically related to Java and C++

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     be
    -0.79
     set
    -0.68
     der
    -0.66
     have
    -0.62
     not
    -0.61
     type
    -0.60
     can
    -0.60
     die
    -0.60
     
    -0.59
     small
    -0.59
    POSITIVE LOGITS
     myſelf
    1.09
     snippetHide
    1.09
     pleaſure
    1.07
     purpoſe
    1.06
     EconPapers
    1.05
     initComponents
    1.04
     ſche
    1.02
     Reſ
    1.00
    Personendaten
    1.00
     carvings
    0.99
    Activations Density 1.490%

    No Known Activations