© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4781
    Prev
    Next
    INDEX
    Explanations

    table-like data with numbers, percentages, and statistical symbols

    oai_token-act-pair · gemini-2.0-flash

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     mission
    -0.45
    <eos>
    -0.44
     R
    -0.41
    /
    -0.40
     (
    -0.40
     im
    -0.40
     pass
    -0.38
     I
    -0.38
     A
    -0.38
    ↵↵
    -0.37
    POSITIVE LOGITS
     itſelf
    0.94
     Efq
    0.94
     Theſe
    0.93
     becauſe
    0.90
     myſelf
    0.89
     whoſe
    0.88
     Monfieur
    0.86
     protoimpl
    0.84
    parsedMessage
    0.84
    protoc
    0.83
    Activations Density 2.057%

    No Known Activations