© 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. 13096
    Prev
    Next
    INDEX
    Explanations

    phrases that appear to be proper nouns

    oai_token-act-pair · gemini-2.0-flash

    Code and technical 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
     mismos
    -0.38
     diriger
    -0.36
     Viitattu
    -0.35
     sterk
    -0.35
     vrais
    -0.35
     maux
    -0.34
     goed
    -0.34
     no
    -0.34
     '',
    -0.33
     États
    -0.33
    POSITIVE LOGITS
     models
    0.93
     ſche
    0.91
     directory
    0.91
     events
    0.88
     characters
    0.88
     model
    0.88
     platform
    0.87
     strategy
    0.87
     project
    0.86
     files
    0.86
    Activations Density 32.001%

    No Known Activations