© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13472
    Prev
    Next
    INDEX
    Explanations

    words or letters that might be names or titles of people and/or locations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     يلي
    -0.68
    gestone
    -0.66
    migiano
    -0.55
     Ouverture
    -0.54
    Попис
    -0.54
    olingo
    -0.53
    weil
    -0.53
    ंदीखरीदारी
    -0.52
    gae
    -0.52
    titleMargin
    -0.51
    POSITIVE LOGITS
    BagLayout
    0.76
    astify
    0.75
    InjectAttribute
    0.71
     Efq
    0.68
    principalTable
    0.68
    LookAnd
    0.66
    LEncoder
    0.66
     المعيارى
    0.65
    sizeCache
    0.65
    таратура
    0.64
    Activations Density 0.350%

    No Known Activations