© 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. 13723
    Prev
    Next
    INDEX
    Explanations

    names of cities and regions within Lithuania

    oai_token-act-pair · gemini-2.0-flash

    Lithuania

    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
    Життєпис
    -0.47
    ίος
    -0.43
    ্ম
    -0.41
    ější
    -0.41
     trùng
    -0.41
    ense
    -0.40
    ImageBackground
    -0.40
    睛
    -0.39
    SPATH
    -0.39
    ULLY
    -0.39
    POSITIVE LOGITS
     itſelf
    0.78
     myſelf
    0.74
     Monfieur
    0.72
     ſeveral
    0.66
     Theſe
    0.65
     himſelf
    0.64
    TintMode
    0.63
    Geplaatst
    0.63
     leſs
    0.62
     juſ
    0.61
    Activations Density 0.157%

    No Known Activations