© 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. 4933
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to the features of electronic devices

    oai_token-act-pair · gemini-2.0-flash

    words related to appearance or design

    np_token-act-pair-logits · gpt-4o-mini

    Technical descriptions

    np_max-act-logits · gemini-2.0-flash
    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
    
    -1.20
    новништво
    -0.95
    ंदीखरीदारी
    -0.87
    WithIOException
    -0.83
     pinulongan
    -0.82
     AssemblyCulture
    -0.81
     препратки
    -0.79
    Personendaten
    -0.79
    verwijspagina
    -0.78
     itſelf
    -0.78
    POSITIVE LOGITS
     inter
    0.45
     forma
    0.45
    APORE
    0.45
    Gemeinsame
    0.44
     U
    0.44
    üf
    0.43
     according
    0.42
     in
    0.41
     form
    0.41
     buena
    0.41
    Activations Density 1.438%

    No Known Activations