© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4569
    Prev
    Next
    INDEX
    Explanations

    sentences about education, learning, and courses of study

    oai_token-act-pair · gemini-2.0-flash

    academic disciplines

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

    fields of study

    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
    bootstrapcdn
    -0.57
     flèche
    -0.53
     educativos
    -0.52
    AxisAlignment
    -0.48
     nakalista
    -0.47
     ग्राहक
    -0.46
     eduk
    -0.44
     naselje
    -0.44
     réussite
    -0.44
     nuclé
    -0.44
    POSITIVE LOGITS
     economics
    1.48
     biology
    1.42
     psychology
    1.41
     physics
    1.38
     Economics
    1.34
     Psychology
    1.29
     geology
    1.28
    Economics
    1.26
     chemistry
    1.25
     sociology
    1.24
    Activations Density 5.607%

    No Known Activations