© 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. 3899
    Prev
    Next
    INDEX
    Explanations

    Javascript or Java code

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     L
    -0.58
     del
    -0.52
    ,
    -0.51
    ysz
    -0.50
     &
    -0.50
     tem
    -0.49
    3
    -0.49
     Y
    -0.46
     l
    -0.46
     st
    -0.46
    POSITIVE LOGITS
     Efq
    0.86
     للمعارف
    0.83
    FunctionFlags
    0.77
    脚注の使い方
    0.75
     Theſe
    0.75
     تضيفلها
    0.74
    BufferException
    0.73
    ագրություններ
    0.73
     referenties
    0.72
     myſelf
    0.72
    Activations Density 0.325%

    No Known Activations