© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15614
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people, places, and institutions

    oai_token-act-pair · gemini-2.0-flash

    French academic terminology

    np_token-act-pair-logits · gpt-4o-mini
    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
    Negative Logits
     defaultstate
    -0.63
     Combien
    -0.57
    Билгалдахарш
    -0.53
     Compens
    -0.52
     cref
    -0.49
    ochim
    -0.49
     ويكيپيديا
    -0.49
     '\\;'
    -0.48
     postIndex
    -0.48
    tagHelper
    -0.47
    POSITIVE LOGITS
    oretical
    0.56
     dieux
    0.54
    verwijspagina
    0.54
     =
    0.53
    laştır
    0.52
    ]=$
    0.52
    kozá
    0.49
     pères
    0.48
     sprüche
    0.48
     mourut
    0.47
    Activations Density 1.326%

    No Known Activations