© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12035
    Prev
    Next
    INDEX
    Explanations

    proper names, often associated with legal documents

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    
    -0.47
     feuille
    -0.45
     vectorielles
    -0.43
    tså
    -0.43
    Pref
    -0.42
     Atlántico
    -0.41
     annonces
    -0.41
    بح
    -0.41
     racines
    -0.41
     Guimarães
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.88
    DotNetBar
    0.85
    stateProvider
    0.77
    outSlope
    0.74
    "}")
    0.72
    principalColumn
    0.68
     doInBackground
    0.67
    BindingResult
    0.67
    GeoNames
    0.66
     cherchés
    0.65
    Activations Density 0.906%

    No Known Activations