© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8487
    Prev
    Next
    INDEX
    Explanations

    a mix of names, places and error messages

    oai_token-act-pair · gemini-2.0-flash

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    CppMethod
    -0.70
     congen
    -0.60
    siębior
    -0.57
     Winaray
    -0.56
    \{\\
    -0.55
     ľ
    -0.54
     Efq
    -0.54
     NDEBUG
    -0.54
     Whig
    -0.53
    انتهای
    -0.51
    POSITIVE LOGITS
    triangleright
    0.65
    EME
    0.56
    "=>"
    0.56
    displayquote
    0.56
    rmtree
    0.55
    %;">
    0.55
    rored
    0.54
    ]_{\
    0.54
     [*]
    0.54
    ']}
    0.53
    Activations Density 0.196%

    No Known Activations