© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12717
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and places.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "rule"

    np_token-act-pair-logits · gpt-4o-mini

    Khurasan and governors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ThroughAttribute
    -0.65
    
    -0.59
     betweenstory
    -0.56
    ="">
    -0.55
     initComponents
    -0.54
    httphttps
    -0.53
    ApplicationTests
    -0.52
    достатки
    -0.51
     дописавши
    -0.51
    }');
    -0.51
    POSITIVE LOGITS
     RUE
    0.52
    Rule
    0.49
    faker
    0.47
     Rule
    0.47
     rule
    0.47
    ❉
    0.47
    CAD
    0.47
     Wicidata
    0.46
    constrained
    0.45
    tab
    0.44
    Activations Density 1.994%

    No Known Activations