© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15803
    Prev
    Next
    INDEX
    Explanations

    PHP code related to objects and methods

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ad
    -0.64
     bu
    -0.61
     mo
    -0.61
     sim
    -0.59
     che
    -0.59
    $_['
    -0.58
     green
    -0.57
     V
    -0.57
     li
    -0.57
     II
    -0.56
    POSITIVE LOGITS
     étoient
    0.91
     Efq
    0.90
     avoient
    0.87
     purpoſe
    0.83
    ItemBackground
    0.79
     Theſe
    0.77
     étoit
    0.75
     Monfieur
    0.74
     Diſ
    0.73
     auroit
    0.73
    Activations Density 0.996%

    No Known Activations