© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10405
    Prev
    Next
    INDEX
    Explanations

    uses of the word "school" and related words such as "classroom", "students", "teacher", "class", or "educational"

    oai_token-act-pair · gemini-2.0-flash

    school

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     school
    -1.05
     Jefus
    -1.02
     purpoſe
    -1.01
    RegressionTest
    -1.00
     myſelf
    -0.96
     Majefty
    -0.95
     SCHOOL
    -0.95
     Anſ
    -0.93
     Diſ
    -0.92
     ſche
    -0.91
    POSITIVE LOGITS
    olated
    0.45
     …
    0.45
     {
    0.44
    asikan
    0.43
     […]
    0.42
     –
    0.41
    very
    0.41
    طيع
    0.40
    ziplin
    0.39
    <eos>
    0.39
    Activations Density 0.528%

    No Known Activations