© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15712
    Prev
    Next
    INDEX
    Explanations

    words related to weather, Chinese characters, and programming files/tutorials

    oai_token-act-pair · gemini-2.0-flash

    Mixed documents and languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     it
    -0.60
     
    -0.58
     (
    -0.54
    ,
    -0.54
     and
    -0.54
     in
    -0.52
     &
    -0.52
     the
    -0.49
     $
    -0.47
     I
    -0.47
    POSITIVE LOGITS
     Houſe
    1.05
     Efq
    1.02
     photolibrary
    1.00
     ་་
    0.98
     houſe
    0.96
     myſelf
    0.91
    Vidite
    0.89
     Мексичка
    0.86
     ―――――
    0.85
     Anſ
    0.85
    Activations Density 0.648%

    No Known Activations