© 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. 5459
    Prev
    Next
    INDEX
    Explanations

    various kinds of parameters and form/code names, along with some personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    code and names

    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
     names
    -1.99
     Names
    -1.83
    names
    -1.70
    Names
    -1.61
     NAMES
    -1.60
     naming
    -1.56
     Namen
    -1.55
     NAME
    -1.51
     title
    -1.48
     Name
    -1.48
    POSITIVE LOGITS
     Italijanski
    0.58
     otomatig
    0.58
    windowFixed
    0.52
     ostavi
    0.52
    ništ
    0.51
    expandindo
    0.50
     Савезне
    0.49
    principalColumn
    0.47
     Biôgrafia
    0.47
    Tembelea
    0.46
    Activations Density 1.769%

    No Known Activations