© 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. 9328
    Prev
    Next
    INDEX
    Explanations

    HTML code elements, especially those related to forms, buttons, and style attributes, and javascript functions

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    ↵↵
    -0.87
    .
    -0.80
    ↵
    -0.68
    <eos>
    -0.68
    (
    -0.67
    '
    -0.61
    ,
    -0.56
    _
    -0.56
    -
    -0.55
    "
    -0.54
    POSITIVE LOGITS
    StoryboardSegue
    1.09
    Portale
    1.08
    WebVitals
    1.06
     يتيمه
    1.05
     Jefus
    1.04
     itſelf
    1.04
    ')")
    1.01
    BibitemShut
    1.00
     raiſ
    1.00
     iſt
    0.98
    Activations Density 2.701%

    No Known Activations