© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3198
    Prev
    Next
    INDEX
    Explanations

    first and second person pronouns

    oai_token-act-pair · gemini-2.0-flash

    asking questions

    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
     already
    -0.82
    Already
    -0.81
    already
    -0.79
     Already
    -0.79
     ALREADY
    -0.75
     déjà
    -0.57
    ALREADY
    -0.56
    iss
    -0.54
    已经在
    -0.54
     giải
    -0.52
    POSITIVE LOGITS
     שוליים
    0.79
    FunctionFlags
    0.79
    HtmlAttribute
    0.79
    ContentAsync
    0.74
    ftagPool
    0.70
    ंदीखरीदारी
    0.68
    商品説明
    0.67
    AutoScaleMode
    0.66
     AssemblyCulture
    0.64
     contextLoads
    0.64
    Activations Density 1.399%

    No Known Activations