© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 608
    Prev
    Next
    INDEX
    Explanations

    clauses and phrases using the word "as" that relate one fact to another.

    oai_token-act-pair · gemini-2.0-flash

    too synonym

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    "}")
    -0.48
    caris
    -0.47
    tilles
    -0.46
    》(
    -0.44
    isla
    -0.43
    sams
    -0.43
    BASELINE
    -0.43
     giống
    -0.43
     חיצוניים
    -0.43
    するのは
    -0.42
    POSITIVE LOGITS
     too
    1.92
    too
    1.57
     TOO
    1.47
    Too
    1.46
     Too
    1.45
    TOO
    1.20
     troppo
    0.98
     demasiado
    0.94
     aswell
    0.94
     слишком
    0.91
    Activations Density 1.494%

    No Known Activations