© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13360
    Prev
    Next
    INDEX
    Explanations

    the word "positive" as well as related words like "human"

    oai_token-act-pair · gemini-2.0-flash

    positive

    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
    Negative Logits
    Искәрмәләр
    -0.94
    />";
    -0.85
     ]];
    -0.85
    __":
    -0.83
    "}";
    -0.82
    "],
    -0.82
    __':
    -0.79
    таратура
    -0.77
     Normdatei
    -0.76
    "){
    -0.73
    POSITIVE LOGITS
     assoluto
    0.68
     especialidad
    0.68
     devenus
    0.66
     autrefois
    0.66
     poire
    0.65
     assolu
    0.64
     varones
    0.64
     provisoire
    0.63
     suffit
    0.63
     soins
    0.63
    Activations Density 2.126%

    No Known Activations