© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14611
    Prev
    Next
    INDEX
    Explanations

    content related to educational courses and programs

    oai_token-act-pair · gemini-2.0-flash

    educational course-related terms

    np_token-act-pair-logits · gpt-4o-mini

    course

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    mately
    -0.56
     Baillargeon
    -0.51
     дописавши
    -0.50
    ServletException
    -0.50
    AnchorTagHelper
    -0.49
    Lähteet
    -0.48
    TextWatcher
    -0.48
    ándolo
    -0.47
     '\\;'
    -0.47
    AlterField
    -0.47
    POSITIVE LOGITS
    bootstrapcdn
    0.58
     erbjud
    0.57
     nahilalakip
    0.56
     tilbud
    0.56
     voud
    0.56
     venner
    0.54
     réve
    0.54
     exceptionnel
    0.53
    /*++
    0.52
     transfieras
    0.52
    Activations Density 2.296%

    No Known Activations