© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12595
    Prev
    Next
    INDEX
    Explanations

    mentions of official processes, such as political elections or court trials

    oai_token-act-pair · gemini-2.0-flash

    excerpts from longer texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.59
    enterOuterAlt
    -0.54
    nologue
    -0.53
     propOrder
    -0.50
    rungsseite
    -0.50
    Jeografia
    -0.50
     kasarigan
    -0.50
    autaire
    -0.48
    RegistryLite
    -0.47
     jsPsych
    -0.47
    POSITIVE LOGITS
    CloseOperation
    0.80
     CreateTagHelper
    0.57
    tagHelperRunner
    0.52
    клопе
    0.52
     jadx
    0.51
    出版年
    0.51
    FormTagHelper
    0.49
    Rewrite
    0.48
     would
    0.47
    bodyParser
    0.47
    Activations Density 7.860%

    No Known Activations