© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15583
    Prev
    Next
    INDEX
    Explanations

    years and decades in the 1900s

    oai_token-act-pair · gemini-2.0-flash

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ोंने
    -0.47
     Quay
    -0.44
     đâu
    -0.43
    rolid
    -0.42
     hasard
    -0.41
     ही
    -0.40
    lato
    -0.40
     side
    -0.40
    lat
    -0.40
     bütün
    -0.40
    POSITIVE LOGITS
     MainAxisSize
    0.92
     BoxDecoration
    0.89
    principalColumn
    0.88
     <<<<<<<<<<<<<<
    0.87
    awtextra
    0.87
    WriteTagHelper
    0.82
     StatelessWidget
    0.81
    Datuak
    0.79
    CodedInputStream
    0.77
    InputBorder
    0.75
    Activations Density 2.332%

    No Known Activations