© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3004
    Prev
    Next
    INDEX
    Explanations

    code snippets dealing with symbol tables and JSON objects

    oai_token-act-pair · gemini-2.0-flash

    entry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     typelib
    -0.73
     Audiodateien
    -0.66
    /*
    -0.63
    IContainer
    -0.60
    /**
    -0.59
    rotnie
    -0.59
     للمعارف
    -0.59
    someone
    -0.58
    VideoCapture
    -0.58
    +#+#
    -0.57
    POSITIVE LOGITS
    atsby
    0.54
     Proceso
    0.54
     Stornier
    0.54
    selaer
    0.53
     Cámara
    0.53
    PHEN
    0.52
    pany
    0.52
    rupal
    0.52
    Quelle
    0.51
    rugby
    0.50
    Activations Density 1.738%

    No Known Activations