© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11062
    Prev
    Next
    INDEX
    Explanations

    code or configuration files that deal with transparency and fading, potentially related to CSS.

    oai_token-act-pair · gemini-2.0-flash

    opacity transparency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    addCriterion
    -0.98
    ']))
    -0.90
    Gambas
    -0.83
     كومونز
    -0.82
     defaultstate
    -0.82
     skaters
    -0.81
     متعلقه
    -0.81
     Utilisation
    -0.79
     disambiguazione
    -0.78
    ]));
    -0.77
    POSITIVE LOGITS
    ItemStack
    0.49
    Lucy
    0.39
    ức
    0.36
     primavera
    0.36
    兼
    0.34
     Lucy
    0.33
     i
    0.33
    #
    0.33
     lavoro
    0.32
     colori
    0.32
    Activations Density 2.234%

    No Known Activations