© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 5657
    Prev
    Next
    INDEX
    Explanations

    the word "at"

    oai_token-act-pair · gemini-2.0-flash

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     at
    -0.89
    ↵↵
    -0.86
    ,
    -0.77
     in
    -0.77
     and
    -0.76
     by
    -0.75
     with
    -0.68
     for
    -0.68
     of
    -0.65
     to
    -0.63
    POSITIVE LOGITS
     متعلقه
    1.06
    AddTagHelper
    1.05
    MigrationBuilder
    1.02
     }}"></
    0.97
    RenderAtEndOf
    0.96
     étoit
    0.96
    protoimpl
    0.96
     فريبيس
    0.95
     Geiſt
    0.94
    httphttps
    0.94
    Activations Density 0.235%

    No Known Activations