© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5915
    Prev
    Next
    INDEX
    Explanations

    Japanese text related to programming errors

    oai_token-act-pair · gemini-2.0-flash

    Japanese full stop

    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
    Datuak
    -0.94
    etheless
    -0.84
     تانيه
    -0.83
     سكانية
    -0.80
    fortun
    -0.79
    
    -0.77
     الحره
    -0.76
    berdayakan
    -0.76
     AssemblyCulture
    -0.74
    RetentionPolicy
    -0.71
    POSITIVE LOGITS
    ,
    0.58
     deutscher
    0.57
    に
    0.55
    、
    0.52
     "
    0.51
     -
    0.47
    Coder
    0.47
     معرف
    0.47
    金色
    0.47
    :
    0.46
    Activations Density 0.068%

    No Known Activations