© 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. 6222
    Prev
    Next
    INDEX
    Explanations

    ending curly brackets at the end of a code block

    oai_token-act-pair · gemini-2.0-flash

    }

    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
     kasarigan
    -1.02
    
    -0.89
    ագրություններ
    -0.89
     Савезне
    -0.84
    IntoConstraints
    -0.82
     وتسجيلات
    -0.82
     Мексичка
    -0.81
    évaluateur
    -0.79
    ValueStyle
    -0.77
     ExecuteAsync
    -0.77
    POSITIVE LOGITS
    ↵
    0.72
    ↵↵
    0.69
      
    0.58
    umat
    0.50
     
    0.49
    </strong>
    0.47
          
    0.47
     losing
    0.46
     e
    0.45
    <eos>
    0.45
    Activations Density 1.260%

    No Known Activations