© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2723
    Prev
    Next
    INDEX
    Explanations

    the token "lo" and digits in the range of 2-7

    oai_token-act-pair · gemini-2.0-flash

    technical 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    BeginContext
    -0.58
     createSprite
    -0.54
     Normdatei
    -0.52
    "":
    -0.52
    inib
    -0.51
     насељу
    -0.51
     JpaRepository
    -0.50
    MLLoader
    -0.50
    Toute
    -0.50
     leu
    -0.49
    POSITIVE LOGITS
     blessés
    0.69
     urbanas
    0.62
     препратки
    0.61
     normaux
    0.58
     kvinder
    0.57
     publiques
    0.56
     lâmpada
    0.56
     automatiques
    0.54
     européennes
    0.54
     connues
    0.54
    Activations Density 0.022%

    No Known Activations