© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8747
    Prev
    Next
    INDEX
    Explanations

    words that relate to legal proceedings and geographical locations

    oai_token-act-pair · gemini-2.0-flash

    references to legal or court-related terms

    np_token-act-pair-logits · gpt-4o-mini

    Legal locations and counties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     pylori
    -0.47
     uttry
    -0.47
     gloire
    -0.46
    adalajara
    -0.45
    ưới
    -0.45
     urethra
    -0.44
     alimentaria
    -0.44
    Geographie
    -0.43
    意料
    -0.43
     japonaise
    -0.42
    POSITIVE LOGITS
    IntoConstraints
    0.68
     counties
    0.68
     Marion
    0.67
    +#+#
    0.67
     COUNT
    0.66
     Weld
    0.65
     Montgomery
    0.64
    setViewportView
    0.63
     OMITBAD
    0.61
     Orange
    0.59
    Activations Density 1.886%

    No Known Activations