© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6304
    Prev
    Next
    INDEX
    Explanations

    short descriptive phrases with articles, prepositions, and possessive pronouns

    oai_token-act-pair · gemini-2.0-flash

    carried or received items

    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
    WEBPACK
    -0.62
     Wicidata
    -0.57
    AutoresizingMask
    -0.56
     aéri
    -0.55
    GenerationType
    -0.50
    barten
    -0.48
     assistenza
    -0.47
     riuscito
    -0.47
     bords
    -0.47
     geweest
    -0.47
    POSITIVE LOGITS
     receipt
    0.60
     scarf
    0.59
    Composable
    0.54
     shawl
    0.54
    IsContent
    0.53
     rosary
    0.52
    
    0.52
    énario
    0.50
    inghouse
    0.50
     tricot
    0.50
    Activations Density 2.716%

    No Known Activations