© 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. 11078
    Prev
    Next
    INDEX
    Explanations

    the word "pour" and related words like "involved"

    oai_token-act-pair · gemini-2.0-flash

    pour

    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
     the
    -0.82
      
    -0.73
     on
    -0.72
     a
    -0.72
     (
    -0.71
     one
    -0.68
     to
    -0.67
     in
    -0.67
    IKAN
    -0.65
    ,
    -0.62
    POSITIVE LOGITS
    )";
    0.94
    .")
    0.89
     ")");
    0.88
     ་་
    0.87
    .",
    0.83
    ."]
    0.82
    '".
    0.81
     ddelweddau
    0.81
     
    0.81
    "—
    0.80
    Activations Density 0.829%

    No Known Activations