© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3806
    Prev
    Next
    INDEX
    Explanations

    words that are similar to "like" and adjectives describing size

    oai_token-act-pair · gemini-2.0-flash

    descriptions and comparisons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     moeite
    -0.53
    ografija
    -0.52
    Referencie
    -0.52
     épreuve
    -0.51
     huiles
    -0.50
     *++
    -0.49
     montaje
    -0.49
     Monfieur
    -0.49
     coupable
    -0.48
     defaultstate
    -0.48
    POSITIVE LOGITS
    hyrchwyd
    0.73
     viewDidLoad
    0.60
    liflower
    0.58
    WebElementEntity
    0.57
    elemField
    0.56
    DoubleQuotes
    0.55
    reportWebVitals
    0.53
    oflavin
    0.51
     bowling
    0.51
    ךְ
    0.51
    Activations Density 2.486%

    No Known Activations