© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10017
    Prev
    Next
    INDEX
    Explanations

    code in various programming languages with a bias towards the numerical literals

    oai_token-act-pair · gemini-2.0-flash

    Foreign language fragments

    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
     
    -0.87
    .
    -0.83
     (
    -0.81
    ↵
    -0.81
    <unused62>
    -0.79
    <unused63>
    -0.79
    <unused61>
    -0.79
    ,
    -0.75
    <unused60>
    -0.69
     O
    -0.68
    POSITIVE LOGITS
     Мексичка
    1.72
     Theſe
    1.69
     myſelf
    1.59
     Monfieur
    1.52
     itſelf
    1.49
     Efq
    1.48
     esternos
    1.45
     betweenstory
    1.41
     متعلقه
    1.40
     raiſ
    1.38
    Activations Density 0.140%

    No Known Activations