© 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. 4681
    Prev
    Next
    INDEX
    Explanations

    sentences that use the word "have" and start with "I"

    oai_token-act-pair · gemini-2.0-flash

    conversations/narratives

    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
     am
    -0.49
    WebElementEntity
    -0.49
     ModelExpression
    -0.47
    rypt
    -0.44
    am
    -0.44
    Quint
    -0.42
     ucapnya
    -0.42
    ubic
    -0.41
    masing
    -0.41
    ุ่ม
    -0.41
    POSITIVE LOGITS
     mergeFrom
    0.73
     jsPsych
    0.71
     الدولى
    0.70
     مشين
    0.68
    SharedDtor
    0.66
    ypress
    0.65
    AsUp
    0.64
    setVerticalGroup
    0.63
    RectangleBorder
    0.60
    expandindo
    0.60
    Activations Density 1.077%

    No Known Activations