© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14193
    Prev
    Next
    INDEX
    Explanations

    words related to debugging

    oai_token-act-pair · gemini-2.0-flash

    keyboard keys and actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Personendaten
    -1.01
    MigrationBuilder
    -1.00
     pinulongan
    -0.97
    featureID
    -0.90
     الحره
    -0.87
    DoubleQuotes
    -0.81
    ']))
    -0.80
     disambiguazione
    -0.79
    GIH
    -0.78
    '])){
    -0.78
    POSITIVE LOGITS
     derecho
    0.42
    YTE
    0.38
     speichern
    0.35
    padek
    0.34
    getFullYear
    0.34
    -
    0.34
     F
    0.32
    Interviewer
    0.32
     modifi
    0.32
     U
    0.32
    Activations Density 5.114%

    No Known Activations