© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7013
    Prev
    Next
    INDEX
    Explanations

    words that relate to comparisons or movement from one place to another, and words that denote the size or importance of something

    oai_token-act-pair · gemini-2.0-flash

    large size

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kjelder
    -0.52
    AppRoutingModule
    -0.50
    inquirer
    -0.48
    Dialogs
    -0.47
    setViewName
    -0.46
    autoIncrement
    -0.46
     nyky
    -0.46
    ̸
    -0.46
    AsUp
    -0.45
    izioni
    -0.45
    POSITIVE LOGITS
     big
    2.33
     large
    2.16
    big
    2.08
    large
    1.97
     larger
    1.93
     bigger
    1.86
    Large
    1.81
     Large
    1.79
     LARGE
    1.77
    Big
    1.76
    Activations Density 2.025%

    No Known Activations