© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10690
    Prev
    Next
    INDEX
    Explanations

    code or pseudo-code from a variety of languages or environments

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     chi̍t
    -0.56
    principalTable
    -0.53
    sizeCache
    -0.52
      (
    -0.51
    SPECIFIED
    -0.50
    <bos>
    -0.49
     disponibilités
    -0.47
    kina
    -0.47
     tyle
    -0.44
     <",
    -0.44
    POSITIVE LOGITS
    __))
    0.65
     IndexPath
    0.62
     للمعارف
    0.60
    Personensuche
    0.55
    isContained
    0.51
    ScopeManager
    0.50
     cerrados
    0.50
     CreateTagHelper
    0.50
    featureID
    0.50
     TMPro
    0.48
    Activations Density 1.148%

    No Known Activations