© 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. 1262
    Prev
    Next
    INDEX
    Explanations

    uses of the word "what" followed by states of being or comparisons.

    oai_token-act-pair · gemini-2.0-flash

    defining and explaining

    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
    PositiveButton
    -0.56
    hemiah
    -0.55
    nambuco
    -0.55
     löyty
    -0.53
     exists
    -0.50
    cticut
    -0.50
     occurred
    -0.50
     disappeared
    -0.50
    pierre
    -0.49
    WebMethod
    -0.49
    POSITIVE LOGITS
     propOrder
    0.64
    Doing
    0.61
    expandindo
    0.60
    脚注の使い方
    0.59
     HasFactory
    0.56
     Doing
    0.54
     doing
    0.52
     accomplish
    0.51
    doing
    0.51
     lượt
    0.48
    Activations Density 7.655%

    No Known Activations