© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3676
    Prev
    Next
    INDEX
    Explanations

    the fragment "bir" in various contexts, sometimes as a standalone word, other times as part of a longer word

    oai_token-act-pair · gemini-2.0-flash

    Bir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.94
    s
    -0.54
    cektir
    -0.54
    couz
    -0.53
     bir
    -0.51
    romy
    -0.49
    ада
    -0.49
    return
    -0.49
     birdie
    -0.48
    Bir
    -0.47
    POSITIVE LOGITS
    IonicModule
    0.79
     getItemId
    0.78
    Hochspringen
    0.77
     beginnetje
    0.76
     MessageBoxIcon
    0.75
     архивлан
    0.75
    AddTagHelper
    0.75
    حياته
    0.71
    yntaxException
    0.71
    SpringRunner
    0.71
    Activations Density 0.271%

    No Known Activations