© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10075
    Prev
    Next
    INDEX
    Explanations

    conjunctions within coordinated lists or phrases, especially within technical or academic contexts, and sometimes with a focus on digital signatures or ethical considerations.

    oai_token-act-pair · gemini-2.0-flash

    technical/academic explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     betweenstory
    -0.63
    CONSIN
    -0.62
    <bos>
    -0.61
    ')}}
    -0.54
    iastes
    -0.52
     NSCoder
    -0.52
    ResponseWriter
    -0.50
    ))->
    -0.49
    peteer
    -0.49
     BitSet
    -0.49
    POSITIVE LOGITS
    uarts
    0.50
    (:,:,
    0.48
    hmigung
    0.45
     porcentual
    0.45
     parietal
    0.44
    maßen
    0.44
    Modern
    0.43
    modern
    0.43
     dintr
    0.43
     sekaligus
    0.43
    Activations Density 0.622%

    No Known Activations