© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13702
    Prev
    Next
    INDEX
    Explanations

    words frequently used in English, and some domain specific language

    oai_token-act-pair · gemini-2.0-flash

    professions and experts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     experts
    -0.73
     Experts
    -0.73
     Expert
    -0.73
     especialistas
    -0.69
    Experts
    -0.68
     Specialists
    -0.66
    Expert
    -0.66
     specialists
    -0.65
     Experten
    -0.65
    Specialist
    -0.64
    POSITIVE LOGITS
    DoubleQuotes
    0.62
     jScrollPane
    0.60
    newArrayList
    0.55
    SequentialGroup
    0.55
     jLabel
    0.55
    Билгалдахарш
    0.54
    ioutil
    0.53
     man
    0.51
     Pensions
    0.51
    sequelize
    0.50
    Activations Density 2.783%

    No Known Activations