© 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. 14655
    Prev
    Next
    INDEX
    Explanations

    Japanese text mixed in with english and Chinese words related to sending data

    oai_token-act-pair · gemini-2.0-flash

    Chinese characters

    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
     “
    -0.68
     "
    -0.66
     il
    -0.64
     „
    -0.64
    ,
    -0.63
     u
    -0.62
     y
    -0.61
     ir
    -0.60
     (
    -0.59
     in
    -0.58
    POSITIVE LOGITS
    <bos>
    2.16
     myſelf
    1.79
     itſelf
    1.72
     pleaſure
    1.51
    ſelf
    1.50
     ſtate
    1.48
     Monfieur
    1.48
     Efq
    1.46
     themſelves
    1.45
     ſta
    1.45
    Activations Density 2.340%

    No Known Activations