© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2826
    Prev
    Next
    INDEX
    Explanations

    mentions of something called Edo State

    oai_token-act-pair · gemini-2.0-flash

    State

    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
    Negative Logits
    WIP
    -0.54
    GeneratedValue
    -0.54
    CustomAttributes
    -0.53
    endpush
    -0.52
     aikana
    -0.50
    toCharArray
    -0.50
     vigne
    -0.49
     WIP
    -0.48
     فريبيس
    -0.48
    Delimited
    -0.47
    POSITIVE LOGITS
     مشين
    0.62
    #
    0.57
     Combien
    0.51
    InputTagHelper
    0.50
    InitVars
    0.50
     postIndex
    0.48
    acterium
    0.47
    stanley
    0.47
     gainera
    0.47
    Reporter
    0.47
    Activations Density 0.661%

    No Known Activations