© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12487
    Prev
    Next
    INDEX
    Explanations

    the word "of" preceded by common nouns, often in directional or instructive contexts

    oai_token-act-pair · gemini-2.0-flash

    say "way"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    twimg
    -0.90
    MessageTagHelper
    -0.77
     Meksiku
    -0.75
    mybatisplus
    -0.72
    Jeografia
    -0.71
    Personensuche
    -0.69
    principalColumn
    -0.67
    RegistryLite
    -0.65
    Sklici
    -0.64
     bezeichneter
    -0.64
    POSITIVE LOGITS
     way
    4.09
    Way
    2.98
    way
    2.95
     Way
    2.92
     WAY
    2.86
    WAY
    2.53
     ways
    2.28
    ways
    1.95
     Ways
    1.87
    Ways
    1.84
    Activations Density 12.871%

    No Known Activations