© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11490
    Prev
    Next
    INDEX
    Explanations

    pieces of code that are likely related to pointers or memory addresses in C-like languages, especially when also seeing "nil"

    oai_token-act-pair · gemini-2.0-flash

    nil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ßten
    -0.55
    OUNT
    -0.54
    itename
    -0.49
     ένας
    -0.46
    indsay
    -0.46
    ítés
    -0.45
     veren
    -0.45
    まま
    -0.45
    ORIA
    -0.44
    InMillis
    -0.44
    POSITIVE LOGITS
    AlterField
    0.68
     beginnetje
    0.66
    NameInMap
    0.65
    MigrationBuilder
    0.64
    はじめに
    0.63
    WarningLevel
    0.63
    AccessorTable
    0.60
    SourceChecksum
    0.57
     transfieras
    0.57
     createSlice
    0.57
    Activations Density 1.190%

    No Known Activations