© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10564
    Prev
    Next
    INDEX
    Explanations

    code-related text with a wide variety of symbols and keywords, potentially related to configuration or assignment.

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     تضيفلها
    -0.57
     ModelExpression
    -0.53
     there
    -0.48
    LookAnd
    -0.45
    FILL
    -0.45
    principalTable
    -0.44
     чему
    -0.44
    InstrumentedTest
    -0.42
    >");
    -0.42
    ThroughAttribute
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    0.70
    indd
    0.65
    }{*}{}
    0.60
     aDecoder
    0.58
    новништво
    0.57
    PhysRev
    0.56
     iſt
    0.54
    UVWXYZ
    0.53
    bkz
    0.53
    AMIENTO
    0.52
    Activations Density 1.387%

    No Known Activations