© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13407
    Prev
    Next
    INDEX
    Explanations

    punctuation, author names, and superlative words

    oai_token-act-pair · gemini-2.0-flash

    Reviews and commentary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     very
    -0.97
     amazing
    -0.94
     extremely
    -0.93
     incredibly
    -0.90
     beautifully
    -0.82
     superbly
    -0.82
     gorgeous
    -0.82
     stunning
    -0.82
     perfectly
    -0.82
     really
    -0.82
    POSITIVE LOGITS
    tagHelperRunner
    0.85
    RegressionTest
    0.69
    LookAnd
    0.62
    SourceChecksum
    0.60
    Geplaatst
    0.60
     defendants
    0.59
     jScrollPane
    0.57
    webElementXpaths
    0.57
    HasColumnName
    0.57
     <<<<<<<<<<<<<<
    0.56
    Activations Density 4.137%

    No Known Activations