© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12427
    Prev
    Next
    INDEX
    Explanations

    a combination of programming code and political commentary or warnings.

    oai_token-act-pair · gemini-2.0-flash

    Politics and Technology

    np_max-act · 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
     referenties
    -0.55
     indeb
    -0.54
    UnknownFieldSet
    -0.52
    omock
    -0.52
    ########.
    -0.50
     WOR
    -0.49
     lans
    -0.48
    Market
    -0.48
     дописавши
    -0.47
     unknownFields
    -0.47
    POSITIVE LOGITS
    rawDesc
    0.69
    PreferredItem
    0.60
    MergeFrom
    0.57
    róż
    0.55
    ToOne
    0.53
    CodedInputStream
    0.52
    öbb
    0.52
    complexContent
    0.49
    obel
    0.48
    currentColor
    0.48
    Activations Density 7.448%

    No Known Activations