© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12391
    Prev
    Next
    INDEX
    Explanations

    text related to genomic sequencing, including primers, human genome references, and sequencing instruments.

    oai_token-act-pair · gemini-2.0-flash

    human genome

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     snippetHide
    -0.62
     sumpay
    -0.60
    neté
    -0.56
    enumii
    -0.56
    abestanden
    -0.56
     архивлан
    -0.54
    DialogContent
    -0.51
     nahilalakip
    -0.50
     utafitiHapana
    -0.49
    nsf
    -0.49
    POSITIVE LOGITS
    Geplaatst
    0.55
    twimg
    0.54
    richTextPanel
    0.52
    Aktualisiert
    0.51
     NKC
    0.50
     Finish
    0.49
     finish
    0.49
     Mannes
    0.49
    cetti
    0.48
    vestream
    0.48
    Activations Density 3.438%

    No Known Activations