© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12865
    Prev
    Next
    INDEX
    Explanations

    the word "balance" and related concepts about keeping things in proportion

    oai_token-act-pair · gemini-2.0-flash

    Finding balance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ftagPool
    -0.52
     ),
    -0.49
    ¹)
    -0.47
     cos
    -0.47
    orgh
    -0.46
     flanks
    -0.46
    FormBuilder
    -0.45
     bulkhead
    -0.45
    getColumnIndex
    -0.44
    ()))
    -0.44
    POSITIVE LOGITS
     blessés
    0.66
     سكانية
    0.65
     Мексичка
    0.63
    MemoryWarning
    0.62
     offerts
    0.61
     vectorielles
    0.60
     Meksiku
    0.59
     couverts
    0.58
     travailleurs
    0.58
     vectoriales
    0.58
    Activations Density 3.210%

    No Known Activations