© 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. 3536
    Prev
    Next
    INDEX
    Explanations

    questions that may indicate critical thinking or inquiry ("why" questions)

    oai_token-act-pair · gemini-2.0-flash

    why

    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
     Need
    -0.81
    Need
    -0.74
     how
    -0.67
     need
    -0.66
    How
    -0.66
    need
    -0.65
    how
    -0.60
     How
    -0.59
    Why
    -0.55
     NEED
    -0.55
    POSITIVE LOGITS
    发表于
    1.02
     مشين
    0.97
     الرياضيه
    0.96
    OrBuilder
    0.96
    AddTagHelper
    0.96
     للمعارف
    0.94
     <=",
    0.92
     Efq
    0.91
     متعلقه
    0.91
    :✨
    0.91
    Activations Density 1.916%

    No Known Activations