© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5566
    Prev
    Next
    INDEX
    Explanations

    words relating to home organization and unpacking

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     perfección
    -0.54
     américains
    -0.45
     posee
    -0.45
     solides
    -0.44
    AnimationsModule
    -0.43
     hipó
    -0.43
    Fns
    -0.43
     getDefault
    -0.43
     merve
    -0.43
     gode
    -0.42
    POSITIVE LOGITS
     XCTest
    0.69
     actionMode
    0.65
     viewType
    0.64
     Parcelable
    0.60
    oneofs
    0.58
    eroom
    0.58
    complexType
    0.58
    ViewInit
    0.57
     AssemblyCompany
    0.56
    oleum
    0.56
    Activations Density 2.476%

    No Known Activations