© 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. 4582
    Prev
    Next
    INDEX
    Explanations

    the name "Dar(number)"

    oai_token-act-pair · gemini-2.0-flash

    Dar

    np_max-act-logits · 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
    migrationBuilder
    -0.66
    SequentialGroup
    -0.52
    abinieri
    -0.49
    irov
    -0.49
    styrelsen
    -0.49
    tymologie
    -0.48
    rogly
    -0.48
    bootstrapcdn
    -0.47
    datatables
    -0.47
    modelBuilder
    -0.47
    POSITIVE LOGITS
    IsContent
    0.70
    Personendaten
    0.68
     createState
    0.55
     EconPapers
    0.55
     nahilalakip
    0.55
    OGND
    0.54
     defStyleAttr
    0.54
    DockStyle
    0.54
    queryInterface
    0.54
     Roskov
    0.54
    Activations Density 0.315%

    No Known Activations