© 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. 14215
    Prev
    Next
    INDEX
    Explanations

    technical biological experimental procedure descriptions and results.

    oai_token-act-pair · gemini-2.0-flash

    control marker

    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
    oredCriteria
    -0.86
    ⓧ
    -0.77
     صوتيه
    -0.75
    PYX
    -0.75
     nahilalakip
    -0.74
    UpInside
    -0.72
    CodedInputStream
    -0.71
    cipar
    -0.71
    rungsseite
    -0.70
    lwjgl
    -0.69
    POSITIVE LOGITS
     '\\;'
    0.66
     randomly
    0.51
    once
    0.50
     gốc
    0.49
    łek
    0.48
     once
    0.48
     random
    0.48
    deau
    0.47
    net
    0.47
     sombra
    0.47
    Activations Density 5.362%

    No Known Activations