© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13434
    Prev
    Next
    INDEX
    Explanations

    words vaguely related to a variety of academic fields, especially those with technical language, fairy tales, or medicine.

    oai_token-act-pair · gemini-2.0-flash

    tions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <eos>
    -0.63
    </strong>
    -0.57
    .
    -0.56
    ),
    -0.53
     (
    -0.53
    </em>
    -0.52
    ,
    -0.52
    )
    -0.47
     ErrIntOverflow
    -0.47
    ↵↵
    -0.46
    POSITIVE LOGITS
     myſelf
    1.35
     Efq
    1.31
    <bos>
    1.27
     itſelf
    1.25
     Theſe
    1.14
     Jefus
    1.12
     ſeveral
    1.12
     themſelves
    1.12
     ―――――
    1.10
     pleaſure
    1.09
    Activations Density 21.983%

    No Known Activations