© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4232
    Prev
    Next
    INDEX
    Explanations

    words that come before other words that it seeks; it seems to like "when," "that," "as," and "be."

    oai_token-act-pair · gemini-2.0-flash

    when

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     يتيمه
    -0.58
    :✨
    -0.55
    DoubleQuotes
    -0.52
    principalTable
    -0.51
    Sklici
    -0.50
    🏾
    -0.49
    devamını
    -0.49
     venons
    -0.48
     stie
    -0.48
    reszcie
    -0.47
    POSITIVE LOGITS
     used
    0.99
     taken
    0.95
     eaten
    0.93
     applied
    0.92
    used
    0.91
     administered
    0.89
     deployed
    0.84
     wielded
    0.84
    Used
    0.83
     worn
    0.83
    Activations Density 2.543%

    No Known Activations