© 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. 9795
    Prev
    Next
    INDEX
    Explanations

    the word "garden"

    oai_token-act-pair · gemini-2.0-flash

    garden

    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
    RenderAtEndOf
    -0.53
     màng
    -0.52
     Wing
    -0.52
    AddTagHelper
    -0.51
    Assignments
    -0.51
    assigns
    -0.50
    DispatchToProps
    -0.50
    winged
    -0.49
    IsUnicode
    -0.49
     membrana
    -0.48
    POSITIVE LOGITS
    NameInMap
    0.70
     /\.(
    0.65
    fjspx
    0.60
     AssemblyCulture
    0.55
     stake
    0.52
    bitField
    0.51
    qrstuvwxyz
    0.51
     disambiguazione
    0.50
    utilisons
    0.50
     resourceCulture
    0.50
    Activations Density 1.973%

    No Known Activations