© 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. 10104
    Prev
    Next
    INDEX
    Explanations

    german words, particularly those related to language and research funding

    oai_token-act-pair · gemini-2.0-flash

    code/research/foreign language

    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
     trouverez
    -0.50
     fédé
    -0.47
     saisi
    -0.47
     nourriture
    -0.45
    ather
    -0.44
    ADELPHIA
    -0.44
    Bronnen
    -0.43
     liitty
    -0.42
    dier
    -0.41
     peores
    -0.41
    POSITIVE LOGITS
    CodedInputStream
    0.69
     lenker
    0.69
    JoinTable
    0.63
     Савезне
    0.63
     TreeNode
    0.61
     '\\;'
    0.61
     intptr
    0.61
    تفصیلات
    0.61
    ValueGeneration
    0.59
    devamını
    0.59
    Activations Density 0.265%

    No Known Activations