© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15276
    Prev
    Next
    INDEX
    Explanations

    numbers and number-related formatting

    oai_token-act-pair · gemini-2.0-flash

    numbers and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     препратки
    -0.97
    Datuak
    -0.96
    MigrationBuilder
    -0.94
    DoubleQuotes
    -0.94
     MainAxisSize
    -0.92
    setVerticalGroup
    -0.89
     AssemblyCulture
    -0.88
    ValueStyle
    -0.87
    extAlignment
    -0.86
     оригіналу
    -0.85
    POSITIVE LOGITS
     AssemblyVersion
    0.52
    于
    0.42
     (
    0.41
     Jordan
    0.40
     bpy
    0.40
    InfoService
    0.39
     William
    0.38
     الدين
    0.37
    GINIA
    0.37
     erec
    0.37
    Activations Density 2.942%

    No Known Activations