© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15520
    Prev
    Next
    INDEX
    Explanations

    code snippets or technical specifications about flight controllers and I2C sensors

    oai_token-act-pair · gemini-2.0-flash

    Programming tokens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    SourceChecksum
    -0.66
     Wikimedijinoj
    -0.45
     kaarangay
    -0.44
     initComponents
    -0.43
    ">—
    -0.43
     homen
    -0.42
    izoen
    -0.41
    таратура
    -0.40
     dilation
    -0.40
     Jaros
    -0.39
    POSITIVE LOGITS
    \{\\
    0.73
    posedge
    0.67
    CppCodeGen
    0.67
     prop
    0.64
     })}
    0.64
    !")
    0.63
     Prop
    0.63
     ESC
    0.62
    //});
    0.61
    StructEnd
    0.60
    Activations Density 0.823%

    No Known Activations