© 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. 4445
    Prev
    Next
    INDEX
    Explanations

    HTML and React code and blog post excerpts including "continue reading"

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     المعيارى
    -0.74
     مرئيه
    -0.73
     BorderRadius
    -0.73
     in
    -0.68
    StructEnd
    -0.67
    ंदीखरीदारी
    -0.65
    tagHelperRunner
    -0.64
     Dernière
    -0.63
    expandindo
    -0.63
     autorytatywna
    -0.61
    POSITIVE LOGITS
     varandra
    0.71
     équipements
    0.66
     bénéfices
    0.66
     ögon
    0.64
     vänner
    0.63
     tiroirs
    0.60
     avoient
    0.59
     oreilles
    0.59
     äldre
    0.59
     récompenses
    0.59
    Activations Density 13.013%

    No Known Activations