© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14155
    Prev
    Next
    INDEX
    Explanations

    code snippets by matching keywords like "type", "class", "function", and "array"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ujednoznacz
    -0.81
    SBATCH
    -0.70
    elemField
    -0.69
    saraba
    -0.68
    GraphicsUnit
    -0.67
    politico
    -0.63
    lucene
    -0.61
    abetes
    -0.60
    createCell
    -0.59
    %)$
    -0.58
    POSITIVE LOGITS
     pleaſure
    0.70
     Reſ
    0.65
     enfans
    0.65
     Monfieur
    0.64
     paille
    0.62
     Majefty
    0.60
     téléph
    0.59
     polizia
    0.58
     juges
    0.58
     greateſt
    0.58
    Activations Density 1.435%

    No Known Activations