© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4713
    Prev
    Next
    INDEX
    Explanations

    HTML and Javascript code, specifically related to buttons, forms, and class names.

    oai_token-act-pair · gemini-2.0-flash

    HTML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     n
    -0.57
     ar
    -0.55
     D
    -0.53
     due
    -0.53
     but
    -0.52
     forma
    -0.52
     part
    -0.52
     re
    -0.51
     a
    -0.50
    .
    -0.50
    POSITIVE LOGITS
     myſelf
    1.18
     itſelf
    1.13
     himſelf
    1.08
     themſelves
    1.08
    ſelf
    1.06
     ſeveral
    1.06
     pleaſure
    1.03
    Vidite
    1.02
     ſtate
    1.01
     Efq
    1.00
    Activations Density 3.987%

    No Known Activations