© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14340
    Prev
    Next
    INDEX
    Explanations

    instances of learning and teaching being described

    oai_token-act-pair · gemini-2.0-flash

    learn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    urlpatterns
    -0.49
    ็จ
    -0.45
     arrivé
    -0.43
     livré
    -0.41
     dalamnya
    -0.40
     vœ
    -0.40
    úgó
    -0.40
     зав
    -0.39
    __',
    -0.39
     departamentos
    -0.39
    POSITIVE LOGITS
    JAXB
    0.69
    httphttps
    0.68
     Mucha
    0.64
    mişti
    0.63
    intios
    0.59
    ByIndex
    0.59
    makeConstraints
    0.59
     life
    0.59
    oredCriteria
    0.58
    TagHelper
    0.58
    Activations Density 9.337%

    No Known Activations