© 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. 10388
    Prev
    Next
    INDEX
    Explanations

    calls to action involving clicking and reading

    oai_token-act-pair · gemini-2.0-flash

    here

    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
    ^(@)
    -1.12
    )";
    -0.99
    ".
    -0.97
    ]--;
    -0.96
    $.
    -0.94
    ")));
    -0.94
    "):
    -0.93
    Sucesor
    -0.91
    ."</
    -0.91
    "],
    -0.90
    POSITIVE LOGITS
    <strong>
    0.92
     
    0.88
    <eos>
    0.83
      
    0.81
    ↵
    0.76
    .
    0.74
    s
    0.74
    1
    0.73
    <h3>
    0.71
    2
    0.71
    Activations Density 0.612%

    No Known Activations