© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14722
    Prev
    Next
    INDEX
    Explanations

    negative political and economic actions by foreign powers.

    oai_token-act-pair · gemini-2.0-flash

    imperial

    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
    adaptiveStyles
    -0.83
     ProtoMessage
    -0.80
    sizeCache
    -0.69
     utafitiHapana
    -0.69
     combineReducers
    -0.66
     unknownFields
    -0.66
     AssemblyCulture
    -0.66
     CreateTagHelper
    -0.65
     EconPapers
    -0.63
     Normdatei
    -0.61
    POSITIVE LOGITS
     imperial
    0.72
     Imperial
    0.69
    Imperial
    0.66
     post
    0.59
    neo
    0.59
     colon
    0.57
    imperial
    0.56
     colonie
    0.56
    post
    0.55
     colony
    0.54
    Activations Density 1.739%

    No Known Activations