© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8125
    Prev
    Next
    INDEX
    Explanations

    HTML button and form elements, especially those with specific class names like "btn", "form", and "option".

    oai_token-act-pair · gemini-2.0-flash

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Portail
    -0.74
     Савезне
    -0.62
     '\\;'
    -0.56
    tonode
    -0.56
    Portale
    -0.55
    setof
    -0.54
     calendriers
    -0.53
     theils
    -0.52
     Monfieur
    -0.50
    Хьажоргаш
    -0.49
    POSITIVE LOGITS
    makeConstraints
    0.54
    cshtml
    0.51
    +:+
    0.48
    obacterium
    0.42
    findpost
    0.41
    WAKE
    0.40
    kloped
    0.40
    uellement
    0.40
    flashdata
    0.40
    inn
    0.39
    Activations Density 2.256%

    No Known Activations