© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13208
    Prev
    Next
    INDEX
    Explanations

    words that might appear in a mathematical proof

    oai_token-act-pair · gemini-2.0-flash

    assumption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     resourceCulture
    -0.52
    Autowired
    -0.49
     Known
    -0.48
    endid
    -0.48
    Fleur
    -0.47
    colage
    -0.46
    sprechend
    -0.46
     Crus
    -0.45
    particip
    -0.45
    ɵ
    -0.45
    POSITIVE LOGITS
     betweenstory
    1.16
    ArrowToggle
    0.79
    ########.
    0.75
     EconPapers
    0.73
    AndroidJUnit
    0.71
     InputDecoration
    0.68
    featureID
    0.67
    aarrggbb
    0.66
     nahilalakip
    0.63
    ForValue
    0.62
    Activations Density 2.102%

    No Known Activations