© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6779
    Prev
    Next
    INDEX
    Explanations

    common words such as "but", "yes", "the", "we", "just", "passing", "sure", "not", etc. in conjunction with numbers or punctuation

    oai_token-act-pair · gemini-2.0-flash

    instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SequentialGroup
    -0.83
     propOrder
    -0.75
    OrBuilder
    -0.71
    RTEX
    -0.70
    Begriffsklä
    -0.68
     HttpNotFound
    -0.68
    awtextra
    -0.67
     kän
    -0.67
     culturelles
    -0.66
    MemoryWarning
    -0.65
    POSITIVE LOGITS
     look
    0.65
     assume
    0.54
     try
    0.53
    usus
    0.53
     using
    0.52
     Pollack
    0.51
     tri
    0.50
     hear
    0.50
    using
    0.48
     respond
    0.48
    Activations Density 4.319%

    No Known Activations