© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12374
    Prev
    Next
    INDEX
    Explanations

    HTML markup, specifically newsletter issue numbers, the word "News", and possibly also math symbols

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    </em>
    -3.06
    </u>
    -2.84
    </i>
    -2.72
    </h6>
    -2.72
    </h2>
    -2.64
    </h5>
    -2.47
    </strong>
    -2.45
    </code>
    -2.44
    </h4>
    -2.33
    }*/
    -2.25
    POSITIVE LOGITS
    permitAll
    0.62
    aritions
    0.57
    jsonPath
    0.57
    crites
    0.57
     MediatR
    0.56
     étoit
    0.54
     CWE
    0.54
    inghouse
    0.54
     $_[
    0.54
    Rujukan
    0.53
    Activations Density 0.951%

    No Known Activations