© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8257
    Prev
    Next
    INDEX
    Explanations

    fragments of sentences in Q&A format about technical issues

    oai_token-act-pair · gemini-2.0-flash

    Power

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    hap
    -0.39
    ere
    -0.37
    itor
    -0.37
    е
    -0.36
     LLP
    -0.36
    multi
    -0.36
    dd
    -0.36
    und
    -0.36
     Light
    -0.36
    ↵↵
    -0.35
    POSITIVE LOGITS
    WithIOException
    0.94
    TintMode
    0.91
     viewDidLoad
    0.88
     BoxFit
    0.88
    TagMode
    0.82
    GEBURTSDATUM
    0.80
    onAttach
    0.79
    httphttps
    0.77
    MigrationBuilder
    0.76
     ſtate
    0.76
    Activations Density 0.861%

    No Known Activations