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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11780
    Prev
    Next
    INDEX
    Explanations

    language related to education, specifically career planning integrated into schools

    oai_token-act-pair · gemini-2.0-flash

    Learning and education

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     curriculum
    -1.03
    curriculum
    -1.01
    Curriculum
    -0.99
     Curriculum
    -0.91
     cur
    -0.78
     Cur
    -0.75
     curricula
    -0.75
    curricular
    -0.73
    RICULUM
    -0.72
    classroom
    -0.71
    POSITIVE LOGITS
     CreateTagHelper
    0.61
    addCriterion
    0.60
     Theſe
    0.57
     Monfieur
    0.52
     tranſ
    0.52
     Anſ
    0.52
    subpackage
    0.52
    OGND
    0.52
     Chriſt
    0.52
     &___
    0.51
    Activations Density 2.366%

    No Known Activations