© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11670
    Prev
    Next
    INDEX
    Explanations

    words that indicate large quantities or things that are above average

    oai_token-act-pair · gemini-2.0-flash

    higher

    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
     متعلقه
    -0.98
     Easier
    -0.94
    MessageTagHelper
    -0.91
    Fastest
    -0.90
     Worst
    -0.87
     Faster
    -0.87
     Fastest
    -0.87
    Worst
    -0.84
     Longer
    -0.82
     Bigger
    -0.81
    POSITIVE LOGITS
     good
    0.81
     more
    0.78
     high
    0.77
     great
    0.75
     low
    0.74
     higher
    0.74
     amount
    0.74
     greater
    0.73
     better
    0.73
     level
    0.73
    Activations Density 4.615%

    No Known Activations