© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13220
    Prev
    Next
    INDEX
    Explanations

    aggressive or sarcastic language and/or imperative statements.

    oai_token-act-pair · gemini-2.0-flash

    Negative comments/arguments

    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
    eseorang
    -0.67
    WebVitals
    -0.66
    Lähteet
    -0.61
    ərbaycan
    -0.61
    PageRoute
    -0.58
    enoord
    -0.57
    Vidite
    -0.56
     esternos
    -0.56
     Substitute
    -0.54
    handleRequest
    -0.54
    POSITIVE LOGITS
     go
    0.53
     mergeFrom
    0.52
     clearly
    0.48
     ProtoMessage
    0.47
     should
    0.46
     deveria
    0.45
    ANNELS
    0.45
    clearly
    0.44
    AlterField
    0.43
    should
    0.43
    Activations Density 1.210%

    No Known Activations