© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3738
    Prev
    Next
    INDEX
    Explanations

    statistical summaries and experimental setups, especially those starting with "a total of"

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    DebuggerNonUser
    -0.59
    amssymb
    -0.59
     agrí
    -0.55
    hasMoreElements
    -0.53
     Beer
    -0.51
    $_.
    -0.51
    PMailer
    -0.51
    board
    -0.50
     board
    -0.50
    BeginInit
    -0.49
    POSITIVE LOGITS
     esternos
    0.71
     approximately
    0.68
     câte
    0.66
     минимум
    0.66
    +:+
    0.62
    ]='\
    0.60
     obicei
    0.58
     sebanyak
    0.57
     تانيه
    0.57
    ographically
    0.57
    Activations Density 1.468%

    No Known Activations