© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9617
    Prev
    Next
    INDEX
    Explanations

    the string "dd" and sometimes short codes separated by dashes

    oai_token-act-pair · gemini-2.0-flash

    dd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    
    -1.58
     propOrder
    -1.57
     bezeichneter
    -1.57
    Personendaten
    -1.55
    Personensuche
    -1.54
    تقاوى
    -1.53
     snippetHide
    -1.50
    styleType
    -1.50
     ModelExpression
    -1.48
    GEBURTSDATUM
    -1.48
    POSITIVE LOGITS
     the
    1.14
     
    1.03
     in
    0.97
     a
    0.94
    .
    0.93
     an
    0.90
    ,
    0.86
     have
    0.83
     R
    0.83
     no
    0.81
    Activations Density 3.340%

    No Known Activations