© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9805
    Prev
    Next
    INDEX
    Explanations

    seemingly random code snippets and also phrases containing the word "was" or gerunds and the preposition "at"

    oai_token-act-pair · gemini-2.0-flash

    Code and year-related contexts

    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
     four
    -0.52
    4
    -0.51
    八
    -0.48
     Four
    -0.48
     eight
    -0.47
    8
    -0.44
    6
    -0.44
    四
    -0.43
     six
    -0.42
    4
    -0.41
    POSITIVE LOGITS
    migrationBuilder
    0.81
     Chwiliwch
    0.74
    InitVars
    0.74
    WithEmail
    0.69
    AccessorTable
    0.69
     Seven
    0.68
    enderror
    0.68
    شهاد
    0.64
     sieben
    0.63
    utives
    0.62
    Activations Density 1.193%

    No Known Activations