© 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. 2954
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives, particularly those relating to appearance, and the word "look"

    oai_token-act-pair · gemini-2.0-flash

    look

    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
     CreateTagHelper
    -0.66
     onOptions
    -0.58
     OMITTED
    -0.57
    Revenir
    -0.56
     attempt
    -0.56
    Hô
    -0.56
     intentar
    -0.56
     pinulongan
    -0.55
     Mc
    -0.54
    mathscr
    -0.52
    POSITIVE LOGITS
     Efq
    0.70
    printStackTrace
    0.68
    MeasureSpec
    0.68
     Shakspeare
    0.66
     Jefus
    0.66
     Majefty
    0.65
    <bos>
    0.62
     WaitForSeconds
    0.62
    ſelves
    0.61
     circonst
    0.60
    Activations Density 0.071%

    No Known Activations