© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10630
    Prev
    Next
    INDEX
    Explanations

    questions, especially important or rhetorical ones

    oai_token-act-pair · gemini-2.0-flash

    Asking questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    effort
    -0.59
    ADATA
    -0.57
    udessa
    -0.56
    borderSide
    -0.56
    öglichkeiten
    -0.54
     Effort
    -0.54
    elum
    -0.54
     esfuerzo
    -0.54
     Efforts
    -0.53
    Effort
    -0.53
    POSITIVE LOGITS
     question
    1.75
     questions
    1.62
     Question
    1.52
    question
    1.48
    Question
    1.47
     Questions
    1.37
    Questions
    1.33
     QUESTION
    1.30
    questions
    1.30
     Frage
    1.27
    Activations Density 1.325%

    No Known Activations