© 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. 4665
    Prev
    Next
    INDEX
    Explanations

    negative prefixes and domain-specific jargon related to computer programming, mathematics or physics

    oai_token-act-pair · gemini-2.0-flash

    Documents and files

    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
     Vex
    -0.56
     Neop
    -0.53
     Sma
    -0.53
     censiti
    -0.52
     impregnated
    -0.52
     Brute
    -0.52
     habitu
    -0.51
     Etern
    -0.51
     Hic
    -0.50
     strix
    -0.50
    POSITIVE LOGITS
     file
    0.85
     page
    0.79
     group
    0.75
     book
    0.75
     field
    0.73
     website
    0.72
     project
    0.72
     line
    0.72
     name
    0.71
     site
    0.71
    Activations Density 12.782%

    No Known Activations