© 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. 3992
    Prev
    Next
    INDEX
    Explanations

    the letter D standing alone or followed by a period or hyphen

    oai_token-act-pair · gemini-2.0-flash

    D

    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
    屈
    -0.47
     обо
    -0.46
     Qu
    -0.45
     promise
    -0.45
    禁
    -0.45
    mena
    -0.44
     dire
    -0.44
     pot
    -0.44
    lippe
    -0.43
     par
    -0.43
    POSITIVE LOGITS
     AssemblyProduct
    0.79
     greateſt
    0.77
     purpoſe
    0.73
    IntoConstraints
    0.73
     Diſ
    0.71
     beſt
    0.70
     Shakspeare
    0.70
    MessageTagHelper
    0.70
     auffi
    0.69
     démocr
    0.69
    Activations Density 1.251%

    No Known Activations