© 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
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11200
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is asking a question, expressing curiosity, or presenting an argument

    oai_token-act-pair · gemini-2.0-flash

    Asking and wondering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    AndEndTag
    -1.16
     doInBackground
    -0.94
    IUrlHelper
    -0.90
    addCriterion
    -0.89
    IntoConstraints
    -0.89
     autorytatywna
    -0.88
     الحره
    -0.84
    aarrggbb
    -0.81
    PerformLayout
    -0.80
     fieldNum
    -0.80
    POSITIVE LOGITS
    iseite
    0.45
     st
    0.45
     finas
    0.43
     defining
    0.43
    Why
    0.42
     setting
    0.42
    Defining
    0.41
     Why
    0.40
    रण
    0.40
    ajā
    0.39
    Activations Density 0.360%

    No Known Activations