© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5510
    Prev
    Next
    INDEX
    Explanations

    a mix of mathematical expressions including superscripts and subscripts along with snippets of French and technical jargon.

    oai_token-act-pair · gemini-2.0-flash

    mathematical/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    '
    -0.66
    ’
    -0.63
    <bos>
    -0.57
     
    -0.50
    ]
    -0.49
    ',
    -0.48
    coroutines
    -0.48
    ‘
    -0.47
    </strong>
    -0.47
    "
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.91
     Chwiliwch
    0.85
    featureID
    0.85
    audiovisuel
    0.82
    ">//
    0.81
     AssemblyCulture
    0.79
    StructEnd
    0.79
     '\\;'
    0.77
    énario
    0.76
    oa̍t
    0.73
    Activations Density 6.717%

    No Known Activations