© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 115
    Prev
    Next
    INDEX
    Explanations

    clauses beginning with the word "if"

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     propOrder
    -0.85
    AndEndTag
    -0.84
     مشين
    -0.82
     avoient
    -0.81
    TagMode
    -0.79
    Geplaatst
    -0.78
     nahilalakip
    -0.78
    SequentialGroup
    -0.77
     AssemblyTitle
    -0.77
     Theſe
    -0.76
    POSITIVE LOGITS
    ise
    0.51
     take
    0.46
    ize
    0.46
    ate
    0.46
    ja
    0.46
     be
    0.45
     decide
    0.45
     it
    0.44
    xt
    0.44
    ida
    0.44
    Activations Density 3.772%

    No Known Activations