© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9891
    Prev
    Next
    INDEX
    Explanations

    the names or identifiers of fields, often including the terms "name", "barcode", or "price".

    oai_token-act-pair · gemini-2.0-flash

    Structured data

    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
     CreateTagHelper
    -0.90
     للمعارف
    -0.81
     InputDecoration
    -0.66
    ^(@
    -0.65
    )";
    -0.64
    tagHelperRunner
    -0.62
     initComponents
    -0.60
    发表于
    -0.59
    WaitGroup
    -0.59
    %";
    -0.58
    POSITIVE LOGITS
     udaler
    0.57
     Taktlose
    0.48
    횟
    0.48
     <>",
    0.42
    buttonShape
    0.41
    OrNil
    0.41
     kuiten
    0.41
     surla
    0.41
    mtrl
    0.40
     too
    0.38
    Activations Density 2.234%

    No Known Activations