© 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. 9410
    Prev
    Next
    INDEX
    Explanations

    what appears to be jumbled data, including numbers, letters, and symbols.

    oai_token-act-pair · gemini-2.0-flash

    digits

    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
    AddTagHelper
    -0.91
     beginnetje
    -0.85
    setVerticalGroup
    -0.84
    Bibliograf
    -0.84
    fortawesome
    -0.82
    makeConstraints
    -0.82
    InjectAttribute
    -0.81
    談社
    -0.80
    帖最后由
    -0.79
    +#+#
    -0.79
    POSITIVE LOGITS
    chappe
    0.35
     sab
    0.35
     czeko
    0.35
    Nilai
    0.34
    onio
    0.33
     volontaire
    0.33
    ва
    0.32
     utro
    0.31
     --
    0.31
    alto
    0.31
    Activations Density 0.948%

    No Known Activations