© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11888
    Prev
    Next
    INDEX
    Explanations

    locations within Lithuania and related military units during World War II

    oai_token-act-pair · gemini-2.0-flash

    Lithuanian locations

    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
     Roskov
    -0.79
    SequentialGroup
    -0.71
     незавершена
    -0.63
    Diweddarwch
    -0.61
    principalTable
    -0.60
    AccessorTable
    -0.59
    TagMode
    -0.58
    Бахар
    -0.57
     INTERESAR
    -0.56
     hObject
    -0.56
    POSITIVE LOGITS
    IBinder
    0.50
     gris
    0.48
    eleste
    0.48
    e
    0.46
     NgModule
    0.45
     ingrat
    0.43
     Krug
    0.43
     integration
    0.43
     integrated
    0.42
     compromiso
    0.41
    Activations Density 0.165%

    No Known Activations