© 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. 4400
    Prev
    Next
    INDEX
    Explanations

    Japanese text related to programming errors, particularly requests for help

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign 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_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
    ,
    -1.02
     
    -1.02
    -
    -0.98
     (
    -0.96
    .
    -0.93
    <eos>
    -0.86
    ↵↵
    -0.84
      
    -0.83
     -
    -0.81
    :
    -0.81
    POSITIVE LOGITS
     myſelf
    2.13
     Efq
    2.11
     Monfieur
    2.09
     itſelf
    1.98
     Majefty
    1.97
     purpoſe
    1.95
     ſeveral
    1.92
     Anſ
    1.92
     pleaſure
    1.92
     ―――――
    1.91
    Activations Density 1.523%

    No Known Activations