© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4718
    Prev
    Next
    INDEX
    Explanations

    parts of words that end in "ed" or contain "U"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    PROLOG
    -0.65
     betweenstory
    -0.59
     TAMBÉM
    -0.56
    IQR
    -0.55
     Sudbury
    -0.55
     Meksiku
    -0.50
    mení
    -0.50
    umbai
    -0.50
     CURIAM
    -0.49
    kann
    -0.48
    POSITIVE LOGITS
    thâu
    0.59
    bledon
    0.56
    ometer
    0.55
    hlmann
    0.54
    ScopeManager
    0.54
    setVerticalGroup
    0.54
    UnknownFieldSet
    0.54
    vold
    0.53
    LayoutConstraint
    0.52
     nî
    0.51
    Activations Density 0.720%

    No Known Activations