© 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. 12525
    Prev
    Next
    INDEX
    Explanations

    code or commands, often with parentheses and specific keywords like "command", "task", "update", or "delete".

    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
    posedge
    -0.61
    TagMode
    -0.56
    GraphicsUnit
    -0.55
    MemoryWarning
    -0.53
    Handlung
    -0.50
    rophore
    -0.47
    ymce
    -0.47
    "}")
    -0.46
     يتيمه
    -0.46
     résistant
    -0.45
    POSITIVE LOGITS
    MockBean
    0.62
    DockStyle
    0.62
    mybatisplus
    0.59
    LoadScene
    0.56
     estekak
    0.55
    SourceChecksum
    0.55
    weds
    0.54
     RequestMethod
    0.53
     المعيارى
    0.53
    routeProvider
    0.52
    Activations Density 18.782%

    No Known Activations