© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9636
    Prev
    Next
    INDEX
    Explanations

    statistics or mathematical discussions

    oai_token-act-pair · gemini-2.0-flash

    figure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    %"),
    -0.81
    "],
    -0.73
    />";
    -0.72
    ])));
    -0.71
    --){
    -0.70
    ']")
    -0.69
    })));
    -0.68
    "]];
    -0.68
     виправивши
    -0.68
    "]).
    -0.67
    POSITIVE LOGITS
    <bos>
    0.88
     value
    0.77
     values
    0.76
    value
    0.66
    GeneratedValue
    0.64
    값
    0.63
     estimates
    0.61
     값
    0.59
     值
    0.57
     Value
    0.57
    Activations Density 2.282%

    No Known Activations